///|
/// The built-in PDF standard 14 font faces.
///
/// These values name the base fonts that a conforming PDF reader is expected
/// to know without an embedded font program. The variants match the canonical
/// PDF names used in `/BaseFont` entries.
pub(all) enum PdfStandardFont {
PdfTimesRoman
PdfTimesBold
PdfTimesItalic
PdfTimesBoldItalic
PdfHelvetica
PdfHelveticaBold
PdfHelveticaOblique
PdfHelveticaBoldOblique
PdfCourier
PdfCourierBold
PdfCourierOblique
PdfCourierBoldOblique
PdfSymbol
PdfZapfDingbats
} derive(Debug, Eq, ToJson)
///|
/// Return the canonical standard-font name without the leading PDF slash.
pub fn PdfStandardFont::name(self : PdfStandardFont) -> String {
match self {
PdfTimesRoman => "Times-Roman"
PdfTimesBold => "Times-Bold"
PdfTimesItalic => "Times-Italic"
PdfTimesBoldItalic => "Times-BoldItalic"
PdfHelvetica => "Helvetica"
PdfHelveticaBold => "Helvetica-Bold"
PdfHelveticaOblique => "Helvetica-Oblique"
PdfHelveticaBoldOblique => "Helvetica-BoldOblique"
PdfCourier => "Courier"
PdfCourierBold => "Courier-Bold"
PdfCourierOblique => "Courier-Oblique"
PdfCourierBoldOblique => "Courier-BoldOblique"
PdfSymbol => "Symbol"
PdfZapfDingbats => "ZapfDingbats"
}
}
///|
/// Compatibility wrapper for `PdfStandardFont::name`.
pub fn pdf_string_of_standard_font(font : PdfStandardFont) -> String {
font.name()
}
///|
fn pdf_text_name(text : String) -> PdfName {
pdf_name_of_bytes(@ascii.encode(text))
}
///|
fn pdf_text_static_name(text : String) -> PdfName {
pdf_name_of_bytes(@ascii.encode(text))
}
///|
let pdf_text_slash_name : PdfName = pdf_text_static_name("/")
///|
let pdf_text_times_roman_name : PdfName = pdf_text_static_name("/Times-Roman")
///|
let pdf_text_times_new_roman_name : PdfName = pdf_text_static_name(
"/TimesNewRoman",
)
///|
let pdf_text_times_bold_name : PdfName = pdf_text_static_name("/Times-Bold")
///|
let pdf_text_times_new_roman_bold_name : PdfName = pdf_text_static_name(
"/TimesNewRoman,Bold",
)
///|
let pdf_text_times_italic_name : PdfName = pdf_text_static_name("/Times-Italic")
///|
let pdf_text_times_new_roman_italic_name : PdfName = pdf_text_static_name(
"/TimesNewRoman,Italic",
)
///|
let pdf_text_times_bold_italic_name : PdfName = pdf_text_static_name(
"/Times-BoldItalic",
)
///|
let pdf_text_times_new_roman_bold_italic_name : PdfName = pdf_text_static_name(
"/TimesNewRoman,BoldItalic",
)
///|
let pdf_text_helvetica_name : PdfName = pdf_text_static_name("/Helvetica")
///|
let pdf_text_arial_name : PdfName = pdf_text_static_name("/Arial")
///|
let pdf_text_helvetica_bold_name : PdfName = pdf_text_static_name(
"/Helvetica-Bold",
)
///|
let pdf_text_arial_bold_name : PdfName = pdf_text_static_name("/Arial,Bold")
///|
let pdf_text_helvetica_oblique_name : PdfName = pdf_text_static_name(
"/Helvetica-Oblique",
)
///|
let pdf_text_arial_italic_name : PdfName = pdf_text_static_name("/Arial,Italic")
///|
let pdf_text_helvetica_bold_oblique_name : PdfName = pdf_text_static_name(
"/Helvetica-BoldOblique",
)
///|
let pdf_text_arial_bold_italic_name : PdfName = pdf_text_static_name(
"/Arial,BoldItalic",
)
///|
let pdf_text_courier_name : PdfName = pdf_text_static_name("/Courier")
///|
let pdf_text_courier_new_name : PdfName = pdf_text_static_name("/CourierNew")
///|
let pdf_text_courier_bold_name : PdfName = pdf_text_static_name("/Courier-Bold")
///|
let pdf_text_courier_new_bold_name : PdfName = pdf_text_static_name(
"/CourierNew,Bold",
)
///|
let pdf_text_courier_oblique_name : PdfName = pdf_text_static_name(
"/Courier-Oblique",
)
///|
let pdf_text_courier_new_italic_name : PdfName = pdf_text_static_name(
"/CourierNew,Italic",
)
///|
let pdf_text_courier_bold_oblique_name : PdfName = pdf_text_static_name(
"/Courier-BoldOblique",
)
///|
let pdf_text_courier_new_bold_italic_name : PdfName = pdf_text_static_name(
"/CourierNew,BoldItalic",
)
///|
let pdf_text_symbol_name : PdfName = pdf_text_static_name("/Symbol")
///|
let pdf_text_zapf_dingbats_name : PdfName = pdf_text_static_name(
"/ZapfDingbats",
)
///|
let pdf_text_identity_h_name : PdfName = pdf_text_static_name("/Identity-H")
///|
let pdf_text_identity_v_name : PdfName = pdf_text_static_name("/Identity-V")
///|
let pdf_text_standard_encoding_name : PdfName = pdf_text_static_name(
"/StandardEncoding",
)
///|
let pdf_text_mac_roman_encoding_name : PdfName = pdf_text_static_name(
"/MacRomanEncoding",
)
///|
let pdf_text_win_ansi_encoding_name : PdfName = pdf_text_static_name(
"/WinAnsiEncoding",
)
///|
let pdf_text_mac_expert_encoding_name : PdfName = pdf_text_static_name(
"/MacExpertEncoding",
)
///|
let pdf_text_font_file_key_name : PdfName = pdf_text_static_name("/FontFile")
///|
let pdf_text_font_file2_key_name : PdfName = pdf_text_static_name("/FontFile2")
///|
let pdf_text_font_file3_key_name : PdfName = pdf_text_static_name("/FontFile3")
///|
let pdf_text_charset_key_name : PdfName = pdf_text_static_name("/CharSet")
///|
let pdf_text_font_descriptor_key_name : PdfName = pdf_text_static_name(
"/FontDescriptor",
)
///|
let pdf_text_font_bbox_key_name : PdfName = pdf_text_static_name("/FontBBox")
///|
let pdf_text_ascent_key_name : PdfName = pdf_text_static_name("/Ascent")
///|
let pdf_text_descent_key_name : PdfName = pdf_text_static_name("/Descent")
///|
let pdf_text_avg_width_key_name : PdfName = pdf_text_static_name("/AvgWidth")
///|
let pdf_text_max_width_key_name : PdfName = pdf_text_static_name("/MaxWidth")
///|
let pdf_text_flags_key_name : PdfName = pdf_text_static_name("/Flags")
///|
let pdf_text_italic_angle_key_name : PdfName = pdf_text_static_name(
"/ItalicAngle",
)
///|
let pdf_text_cap_height_key_name : PdfName = pdf_text_static_name("/CapHeight")
///|
let pdf_text_xheight_key_name : PdfName = pdf_text_static_name("/XHeight")
///|
let pdf_text_stemv_key_name : PdfName = pdf_text_static_name("/StemV")
///|
let pdf_text_subtype_key_name : PdfName = pdf_text_static_name("/Subtype")
///|
let pdf_text_type3_name : PdfName = pdf_text_static_name("/Type3")
///|
let pdf_text_missing_width_key_name : PdfName = pdf_text_static_name(
"/MissingWidth",
)
///|
let pdf_text_widths_key_name : PdfName = pdf_text_static_name("/Widths")
///|
let pdf_text_first_char_key_name : PdfName = pdf_text_static_name("/FirstChar")
///|
let pdf_text_last_char_key_name : PdfName = pdf_text_static_name("/LastChar")
///|
let pdf_text_charprocs_key_name : PdfName = pdf_text_static_name("/CharProcs")
///|
let pdf_text_resources_key_name : PdfName = pdf_text_static_name("/Resources")
///|
let pdf_text_font_matrix_key_name : PdfName = pdf_text_static_name(
"/FontMatrix",
)
///|
let pdf_text_type1_name : PdfName = pdf_text_static_name("/Type1")
///|
let pdf_text_mmtype1_name : PdfName = pdf_text_static_name("/MMType1")
///|
let pdf_text_true_type_name_value : PdfName = pdf_text_static_name("/TrueType")
///|
let pdf_text_base_font_key_name : PdfName = pdf_text_static_name("/BaseFont")
///|
let pdf_text_font_name : PdfName = pdf_text_static_name("/Font")
///|
let pdf_text_encoding_key_name : PdfName = pdf_text_static_name("/Encoding")
///|
let pdf_text_base_encoding_key_name : PdfName = pdf_text_static_name(
"/BaseEncoding",
)
///|
let pdf_text_differences_key_name : PdfName = pdf_text_static_name(
"/Differences",
)
///|
let pdf_text_type0_name : PdfName = pdf_text_static_name("/Type0")
///|
let pdf_text_registry_key_name : PdfName = pdf_text_static_name("/Registry")
///|
let pdf_text_ordering_key_name : PdfName = pdf_text_static_name("/Ordering")
///|
let pdf_text_supplement_key_name : PdfName = pdf_text_static_name("/Supplement")
///|
let pdf_text_w_key_name : PdfName = pdf_text_static_name("/W")
///|
let pdf_text_w2_key_name : PdfName = pdf_text_static_name("/W2")
///|
let pdf_text_dw_key_name : PdfName = pdf_text_static_name("/DW")
///|
let pdf_text_dw2_key_name : PdfName = pdf_text_static_name("/DW2")
///|
let pdf_text_cid_system_info_key_name : PdfName = pdf_text_static_name(
"/CIDSystemInfo",
)
///|
let pdf_text_descendant_fonts_key_name : PdfName = pdf_text_static_name(
"/DescendantFonts",
)
///|
let pdf_text_wmode_key_name : PdfName = pdf_text_static_name("/WMode")
///|
let pdf_text_cmap_name_key_name : PdfName = pdf_text_static_name("/CMapName")
///|
let pdf_text_cmap_type_key_name : PdfName = pdf_text_static_name("/CMapType")
///|
let pdf_text_usecmap_key_name : PdfName = pdf_text_static_name("/UseCMap")
///|
let pdf_text_tounicode_key_name : PdfName = pdf_text_static_name("/ToUnicode")
///|
let pdf_text_type_key_name : PdfName = pdf_text_static_name("/Type")
///|
let pdf_text_font_name_key_name : PdfName = pdf_text_static_name("/FontName")
///|
let pdf_text_length_key_name : PdfName = pdf_text_static_name("/Length")
///|
fn pdf_text_static_single_byte_glyph_name(value : Int) -> PdfName {
let bytes : FixedArray[Byte] = [47, value.to_byte()]
pdf_name_of_bytes(Bytes::from_array(bytes))
}
///|
let pdf_text_glyph_space_name : PdfName = pdf_text_static_name("/space")
///|
fn pdf_text_ascii_basic_latin_glyph_name_for_cache(
code : Int,
standard_quotes : Bool,
) -> PdfName? {
match code {
32 => Some(pdf_text_glyph_space_name)
33 => Some(pdf_text_static_name("/exclam"))
34 => Some(pdf_text_static_name("/quotedbl"))
35 => Some(pdf_text_static_name("/numbersign"))
36 => Some(pdf_text_static_name("/dollar"))
37 => Some(pdf_text_static_name("/percent"))
38 => Some(pdf_text_static_name("/ampersand"))
39 if standard_quotes => Some(pdf_text_static_name("/quoteright"))
39 => Some(pdf_text_static_name("/quotesingle"))
40 => Some(pdf_text_static_name("/parenleft"))
41 => Some(pdf_text_static_name("/parenright"))
42 => Some(pdf_text_static_name("/asterisk"))
43 => Some(pdf_text_static_name("/plus"))
44 => Some(pdf_text_static_name("/comma"))
45 => Some(pdf_text_static_name("/hyphen"))
46 => Some(pdf_text_static_name("/period"))
47 => Some(pdf_text_static_name("/slash"))
48 => Some(pdf_text_static_name("/zero"))
49 => Some(pdf_text_static_name("/one"))
50 => Some(pdf_text_static_name("/two"))
51 => Some(pdf_text_static_name("/three"))
52 => Some(pdf_text_static_name("/four"))
53 => Some(pdf_text_static_name("/five"))
54 => Some(pdf_text_static_name("/six"))
55 => Some(pdf_text_static_name("/seven"))
56 => Some(pdf_text_static_name("/eight"))
57 => Some(pdf_text_static_name("/nine"))
58 => Some(pdf_text_static_name("/colon"))
59 => Some(pdf_text_static_name("/semicolon"))
60 => Some(pdf_text_static_name("/less"))
61 => Some(pdf_text_static_name("/equal"))
62 => Some(pdf_text_static_name("/greater"))
63 => Some(pdf_text_static_name("/question"))
64 => Some(pdf_text_static_name("/at"))
code if code >= 65 && code <= 90 =>
Some(pdf_text_static_single_byte_glyph_name(code))
91 => Some(pdf_text_static_name("/bracketleft"))
92 => Some(pdf_text_static_name("/backslash"))
93 => Some(pdf_text_static_name("/bracketright"))
94 => Some(pdf_text_static_name("/asciicircum"))
95 => Some(pdf_text_static_name("/underscore"))
96 if standard_quotes => Some(pdf_text_static_name("/quoteleft"))
96 => Some(pdf_text_static_name("/grave"))
code if code >= 97 && code <= 122 =>
Some(pdf_text_static_single_byte_glyph_name(code))
123 => Some(pdf_text_static_name("/braceleft"))
124 => Some(pdf_text_static_name("/bar"))
125 => Some(pdf_text_static_name("/braceright"))
126 => Some(pdf_text_static_name("/asciitilde"))
_ => None
}
}
///|
let pdf_text_standard_basic_latin_glyph_names : FixedArray[PdfName?] = FixedArray::makei(
127,
code => pdf_text_ascii_basic_latin_glyph_name_for_cache(code, true),
)
///|
let pdf_text_plain_basic_latin_glyph_names : FixedArray[PdfName?] = FixedArray::makei(
127,
code => pdf_text_ascii_basic_latin_glyph_name_for_cache(code, false),
)
///|
let pdf_text_glyph_control_ht_name : PdfName = pdf_text_static_name(
"/controlHT",
)
///|
let pdf_text_glyph_control_lf_name : PdfName = pdf_text_static_name(
"/controlLF",
)
///|
let pdf_text_glyph_control_ff_name : PdfName = pdf_text_static_name(
"/controlFF",
)
///|
let pdf_text_glyph_control_cr_name : PdfName = pdf_text_static_name(
"/controlCR",
)
///|
fn pdf_text_cached_basic_latin_glyphname(
code : Int,
standard_quotes : Bool,
) -> PdfName? {
if code < 0 || code > 126 {
None
} else if standard_quotes {
pdf_text_standard_basic_latin_glyph_names[code]
} else {
pdf_text_plain_basic_latin_glyph_names[code]
}
}
///|
fn pdf_text_string_of_name(name : PdfName) -> String {
@ascii.decode_lossy(name.bytes())
}
///|
/// Return the canonical PDF name object for this standard font.
///
/// The returned name includes the leading slash in the underlying `PdfName`
/// bytes and is suitable for `/BaseFont` dictionary entries.
pub fn PdfStandardFont::pdf_name(self : PdfStandardFont) -> PdfName {
match self {
PdfTimesRoman => pdf_text_times_roman_name
PdfTimesBold => pdf_text_times_bold_name
PdfTimesItalic => pdf_text_times_italic_name
PdfTimesBoldItalic => pdf_text_times_bold_italic_name
PdfHelvetica => pdf_text_helvetica_name
PdfHelveticaBold => pdf_text_helvetica_bold_name
PdfHelveticaOblique => pdf_text_helvetica_oblique_name
PdfHelveticaBoldOblique => pdf_text_helvetica_bold_oblique_name
PdfCourier => pdf_text_courier_name
PdfCourierBold => pdf_text_courier_bold_name
PdfCourierOblique => pdf_text_courier_oblique_name
PdfCourierBoldOblique => pdf_text_courier_bold_oblique_name
PdfSymbol => pdf_text_symbol_name
PdfZapfDingbats => pdf_text_zapf_dingbats_name
}
}
///|
/// Recognize a standard 14 font from an ASCII PDF font name.
///
/// `name` is expected to include the leading slash, for example
/// `"/Helvetica"`. Common Microsoft aliases such as `/Arial` and
/// `/TimesNewRoman` are accepted for CamlPDF compatibility.
pub fn pdf_standard_font_of_name(name : String) -> PdfStandardFont? {
match name {
"/Times-Roman" | "/TimesNewRoman" => Some(PdfTimesRoman)
"/Times-Bold" | "/TimesNewRoman,Bold" => Some(PdfTimesBold)
"/Times-Italic" | "/TimesNewRoman,Italic" => Some(PdfTimesItalic)
"/Times-BoldItalic" | "/TimesNewRoman,BoldItalic" =>
Some(PdfTimesBoldItalic)
"/Helvetica" | "/Arial" => Some(PdfHelvetica)
"/Helvetica-Bold" | "/Arial,Bold" => Some(PdfHelveticaBold)
"/Helvetica-Oblique" | "/Arial,Italic" => Some(PdfHelveticaOblique)
"/Helvetica-BoldOblique" | "/Arial,BoldItalic" =>
Some(PdfHelveticaBoldOblique)
"/Courier" | "/CourierNew" => Some(PdfCourier)
"/Courier-Bold" | "/CourierNew,Bold" => Some(PdfCourierBold)
"/Courier-Oblique" | "/CourierNew,Italic" => Some(PdfCourierOblique)
"/Courier-BoldOblique" | "/CourierNew,BoldItalic" =>
Some(PdfCourierBoldOblique)
"/Symbol" => Some(PdfSymbol)
"/ZapfDingbats" => Some(PdfZapfDingbats)
_ => None
}
}
///|
/// Recognize a standard 14 font from a byte-oriented PDF name.
///
/// This is the allocation-light variant used while parsing font dictionaries.
/// It accepts the canonical PDF names and the same common aliases as
/// `pdf_standard_font_of_name`.
pub fn pdf_standard_font_of_pdf_name(name : PdfName) -> PdfStandardFont? {
match name {
name if name == pdf_text_times_roman_name ||
name == pdf_text_times_new_roman_name => Some(PdfTimesRoman)
name if name == pdf_text_times_bold_name ||
name == pdf_text_times_new_roman_bold_name => Some(PdfTimesBold)
name if name == pdf_text_times_italic_name ||
name == pdf_text_times_new_roman_italic_name => Some(PdfTimesItalic)
name if name == pdf_text_times_bold_italic_name ||
name == pdf_text_times_new_roman_bold_italic_name =>
Some(PdfTimesBoldItalic)
name if name == pdf_text_helvetica_name || name == pdf_text_arial_name =>
Some(PdfHelvetica)
name if name == pdf_text_helvetica_bold_name ||
name == pdf_text_arial_bold_name => Some(PdfHelveticaBold)
name if name == pdf_text_helvetica_oblique_name ||
name == pdf_text_arial_italic_name => Some(PdfHelveticaOblique)
name if name == pdf_text_helvetica_bold_oblique_name ||
name == pdf_text_arial_bold_italic_name => Some(PdfHelveticaBoldOblique)
name if name == pdf_text_courier_name || name == pdf_text_courier_new_name =>
Some(PdfCourier)
name if name == pdf_text_courier_bold_name ||
name == pdf_text_courier_new_bold_name => Some(PdfCourierBold)
name if name == pdf_text_courier_oblique_name ||
name == pdf_text_courier_new_italic_name => Some(PdfCourierOblique)
name if name == pdf_text_courier_bold_oblique_name ||
name == pdf_text_courier_new_bold_italic_name =>
Some(PdfCourierBoldOblique)
name if name == pdf_text_symbol_name => Some(PdfSymbol)
name if name == pdf_text_zapf_dingbats_name => Some(PdfZapfDingbats)
_ => None
}
}
///|
/// Return a synthetic baseline adjustment for simple standard-font placement.
///
/// The value is derived from the font ascent-like metrics used by the original
/// CamlPDF helpers and is expressed in glyph-space units.
pub fn PdfStandardFont::baseline_adjustment(self : PdfStandardFont) -> Int {
match self {
PdfTimesRoman => 662 / 2
PdfTimesBold => 676 / 2
PdfTimesItalic => 653 / 2
PdfTimesBoldItalic => 669 / 2
PdfHelvetica
| PdfHelveticaBold
| PdfHelveticaOblique
| PdfHelveticaBoldOblique => 718 / 2
PdfCourier | PdfCourierBold | PdfCourierOblique | PdfCourierBoldOblique =>
562 / 2
PdfSymbol => 673 / 2
PdfZapfDingbats => 705 / 2
}
}
///|
/// Return the standard-font `StemV` descriptor value used when writing fonts.
pub fn PdfStandardFont::stemv(self : PdfStandardFont) -> Int {
match self {
PdfTimesRoman => 116
PdfTimesBold => 122
PdfTimesItalic => 105
PdfTimesBoldItalic => 108
PdfHelvetica => 114
PdfHelveticaBold => 123
PdfHelveticaOblique => 127
PdfHelveticaBoldOblique => 136
PdfCourier => 88
PdfCourierBold => 93
PdfCourierOblique => 100
PdfCourierBoldOblique => 104
PdfSymbol => 0
PdfZapfDingbats => 125
}
}
///|
/// Return PDF font descriptor flags for this standard font.
///
/// The flags distinguish symbolic fonts, fixed-pitch Courier faces, and the
/// nonsymbolic roman faces according to the PDF font descriptor bit layout.
pub fn PdfStandardFont::flags(self : PdfStandardFont) -> Int {
match self {
PdfSymbol => 65541
PdfZapfDingbats => 4
PdfCourier | PdfCourierBold | PdfCourierOblique | PdfCourierBoldOblique =>
33
_ => 32
}
}
///|
/// Parsed standard-font data with its active character encoding.
///
/// Standard 14 fonts do not carry embedded metrics in normal PDF files, so
/// extraction combines the font identity with the chosen simple-font encoding.
pub(all) struct PdfStandardFontData {
font : PdfStandardFont
encoding : PdfEncoding
} derive(Debug, Eq, ToJson)
///|
/// Return a compact debug label for this standard font data.
pub fn PdfStandardFontData::debug_name(self : PdfStandardFontData) -> String {
"StandardFont " + self.font.name()
}
///|
/// Reference to an embedded font program stream in a font descriptor.
///
/// The integer is the object number for `/FontFile`, `/FontFile2`, or
/// `/FontFile3`; the constructor records which descriptor key supplied it.
pub(all) enum PdfFontFile {
PdfFontFile(Int)
PdfFontFile2(Int)
PdfFontFile3(Int)
} derive(Debug, Eq, ToJson)
///|
/// Parsed PDF font descriptor metrics and optional embedded font metadata.
///
/// Numeric fields use PDF glyph-space units. `tounicode` stores decoded
/// `/ToUnicode` mappings when the surrounding font dictionary provides them,
/// so text extraction can prefer explicit Unicode mappings over glyph names.
pub(all) struct PdfFontDescriptor {
ascent : Double
descent : Double
avgwidth : Double
maxwidth : Double
flags : Int
fontbbox : PdfRectangle
italicangle : Double
capheight : Double
xheight : Double
stemv : Double
fontfile : PdfFontFile?
charset : Array[PdfName]?
tounicode : Array[(Int, PdfBytes)]?
} derive(Debug, Eq, ToJson)
///|
/// Type 3 font glyph-program data.
///
/// `charprocs` keeps glyph names paired with their drawing streams and
/// `resources` is the Type 3 resource dictionary used when interpreting those
/// glyph programs.
pub(all) struct PdfType3Glyphs {
fontbbox : PdfRectangle
fontmatrix : TransformMatrix
charprocs : Array[(PdfName, PdfObject)]
resources : PdfObject
} derive(Debug, Eq, ToJson)
///|
/// Simple-font subtype recognized by the PDF text layer.
///
/// Type 1, MMType1, Type 3, and TrueType fonts all use one-byte character
/// codes after their encoding differences have been applied.
pub(all) enum PdfSimpleFontType {
PdfType1
PdfMMType1
PdfType3(PdfType3Glyphs)
PdfTrueType
} derive(Debug, Eq, ToJson)
///|
/// Parsed simple-font dictionary.
///
/// The record preserves declared widths and descriptors when present. Missing
/// metrics are resolved from standard-font fallback data where possible.
pub(all) struct PdfSimpleFont {
fonttype : PdfSimpleFontType
basefont : PdfName?
firstchar : Int
lastchar : Int
widths : Array[Int]
fontdescriptor : PdfFontDescriptor?
fontmetrics : Array[Double]?
encoding : PdfEncoding
} derive(Debug, Eq, ToJson)
///|
/// CID-system identity from a CIDFont or CMap dictionary.
///
/// `registry` and `ordering` are stored as PDF bytes because PDF strings are
/// byte sequences, not MoonBit `String` values.
pub(all) struct PdfCIDSystemInfo {
registry : PdfBytes
ordering : PdfBytes
supplement : Int
} derive(Debug, Eq, ToJson)
///|
/// Vertical metrics for a CID in a composite font.
///
/// The fields correspond to the PDF `/W2` tuple: vertical width and horizontal
/// displacement vector components.
pub(all) struct PdfCIDVerticalWidth {
width : Double
vx : Double
vy : Double
} derive(Debug, Eq, ToJson)
///|
/// Parsed descendant CIDFont data for a Type 0 composite font.
///
/// Width arrays are normalized into explicit CID-to-width entries while
/// preserving the PDF default horizontal and vertical widths.
pub(all) struct PdfCompositeCIDFont {
cid_system_info : PdfCIDSystemInfo
cid_basefont : PdfName
cid_fontdescriptor : PdfFontDescriptor
cid_widths : Array[(Int, Double)]
cid_widths2 : Array[(Int, PdfCIDVerticalWidth)]
cid_default_width : Double
cid_default_width2 : Array[Double]
} derive(Debug, Eq, ToJson)
///|
/// CMap source used by a Type 0 font.
///
/// A CMap may be predefined by name, referenced as an external stream object,
/// or parsed from that external stream together with its mapping tables.
pub(all) enum PdfCMapEncoding {
PdfPredefinedCMap(PdfName)
PdfCMap(Int)
PdfExternalCMap(Int, PdfParsedCMap)
} derive(Debug, Eq, ToJson)
///|
/// One parsed CMap code-space range.
///
/// `length` is the character-code byte length, and `first`/`last` are the
/// inclusive packed-byte bounds accepted by that range.
pub(all) struct PdfCMapCodeSpace {
length : Int
first : Int
last : Int
} derive(Debug, Eq, ToJson)
///|
/// Parsed CMap or ToUnicode stream data.
///
/// `map` stores character-code to UTF-16BE bytes from `bfchar`/`bfrange`,
/// `cid_map` stores character-code to CID mappings, and `notdef_map` stores
/// notdef fallback CIDs. Optional metadata is taken from the stream body or
/// stream dictionary when available.
pub(all) struct PdfParsedCMap {
map : Array[(Int, PdfBytes)]
cid_map : Array[(Int, Int)]
notdef_map : Array[(Int, Int)]
codespaces : Array[PdfCMapCodeSpace]
usecmap : PdfName?
wmode : Int?
cmap_name : PdfName?
cmap_type : Int?
cid_system_info : PdfCIDSystemInfo?
} derive(Debug, Eq, ToJson)
///|
/// Parsed Type 0 font with descendant CIDFont and CMap encoding.
pub(all) struct PdfCIDKeyedFont {
basefont : PdfName
composite : PdfCompositeCIDFont
encoding : PdfCMapEncoding
} derive(Debug, Eq, ToJson)
///|
/// Return a compact debug label containing the Type 0 base font name.
pub fn PdfCIDKeyedFont::debug_name(self : PdfCIDKeyedFont) -> String {
"CIDKeyedFont " + pdf_text_string_of_name(self.basefont)
}
///|
/// Test whether this CMap encoding is the predefined `/Identity-H` map.
pub fn PdfCMapEncoding::is_identity_h(self : PdfCMapEncoding) -> Bool {
match self {
PdfPredefinedCMap(name) => name == pdf_text_identity_h_name
_ => false
}
}
///|
/// Test whether this CMap encoding is the predefined `/Identity-V` map.
pub fn PdfCMapEncoding::is_identity_v(self : PdfCMapEncoding) -> Bool {
match self {
PdfPredefinedCMap(name) => name == pdf_text_identity_v_name
_ => false
}
}
///|
fn pdf_text_predefined_cmap_uses_two_byte_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
(
(text.contains("-UCS2-") || text.contains("-UTF16-")) &&
(text.has_suffix("-H") || text.has_suffix("-V"))
) ||
pdf_text_predefined_cmap_uses_japan1_two_byte_charcodes(name)
}
///|
fn pdf_text_predefined_cmap_has_text_orientation(text : String) -> Bool {
text == "/H" || text == "/V" || text.has_suffix("-H") || text.has_suffix("-V")
}
///|
fn pdf_text_predefined_cmap_is_vertical(name : PdfName) -> Bool {
pdf_text_string_of_name(name).has_suffix("-V")
}
///|
fn pdf_text_predefined_cmap_uses_shift_jis_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("RKSJ")
}
///|
fn pdf_text_predefined_cmap_uses_hojo_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("Hojo-EUC")
}
///|
fn pdf_text_predefined_cmap_uses_japan1_two_byte_charcodes(
name : PdfName,
) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
pdf_text_predefined_japan1_cid_ranges(name) is Some(_) &&
!text.contains("RKSJ") &&
!text.contains("EUC")
}
///|
fn pdf_text_predefined_cmap_uses_ucs2_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("-UCS2-")
}
///|
fn pdf_text_predefined_cmap_uses_utf8_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("-UTF8-")
}
///|
fn pdf_text_predefined_cmap_uses_utf16_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("-UTF16-")
}
///|
fn pdf_text_predefined_cmap_uses_utf32_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
(text.contains("-UTF32-") || text.contains("-UCS32-"))
}
///|
fn pdf_text_predefined_cmap_uses_gb_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("GB-EUC")
}
///|
fn pdf_text_predefined_cmap_uses_gbpc_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("GBpc-EUC")
}
///|
fn pdf_text_predefined_cmap_uses_hkscs_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("HKscs-B5")
}
///|
fn pdf_text_predefined_cmap_uses_cns_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("CNS-EUC")
}
///|
fn pdf_text_predefined_cns_euc_cid_ranges(
name : PdfName,
) -> Array[(Int, Int, Int)]? {
guard pdf_text_predefined_cmap_uses_cns_euc_charcodes(name) else {
return None
}
if pdf_text_predefined_cmap_is_vertical(name) {
Some(pdf_text_cns_euc_v_cid_ranges)
} else {
Some(pdf_text_cns_euc_h_cid_ranges)
}
}
///|
fn pdf_text_predefined_cns1_b5_cid_ranges(
name : PdfName,
) -> Array[(Int, Int, Int)]? {
let text = pdf_text_string_of_name(name)
guard pdf_text_predefined_cmap_has_text_orientation(text) else { return None }
if text.contains("ETenms-B5") {
Some(pdf_text_etenms_b5_cid_ranges)
} else if text.contains("HKdla-B5") {
Some(pdf_text_hkdla_b5_cid_ranges)
} else if text.contains("HKdlb-B5") {
Some(pdf_text_hkdlb_b5_cid_ranges)
} else if text.contains("HKgccs-B5") {
Some(pdf_text_hkgccs_b5_cid_ranges)
} else if text.contains("HKm314-B5") {
Some(pdf_text_hkm314_b5_cid_ranges)
} else if text.contains("HKm471-B5") {
Some(pdf_text_hkm471_b5_cid_ranges)
} else {
None
}
}
///|
fn pdf_text_predefined_cmap_uses_cns1_b5_charcodes(name : PdfName) -> Bool {
match pdf_text_predefined_cns1_b5_cid_ranges(name) {
Some(_) => true
None => false
}
}
///|
fn pdf_text_predefined_cmap_uses_big5_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("B5")
}
///|
fn pdf_text_predefined_cmap_uses_b5pc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("B5pc")
}
///|
fn pdf_text_predefined_cmap_uses_uhc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("UHC")
}
///|
fn pdf_text_predefined_cmap_uses_ksc_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("KSC-EUC")
}
///|
fn pdf_text_predefined_cmap_uses_kscpc_euc_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
text.contains("KSCpc-EUC")
}
///|
fn pdf_text_predefined_cmap_uses_gbk2k_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) && text.contains("GBK2K")
}
///|
fn pdf_text_predefined_cmap_uses_gbk_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
(text.contains("GBK-EUC") || text.contains("GBKp-EUC"))
}
///|
fn pdf_text_predefined_cmap_uses_mixed_byte_charcodes(name : PdfName) -> Bool {
let text = pdf_text_string_of_name(name)
pdf_text_predefined_cmap_has_text_orientation(text) &&
(
text.contains("-EUC-") ||
text.has_prefix("/EUC-") ||
text.contains("Hojo-EUC") ||
text.contains("RKSJ") ||
text.contains("B5") ||
text.contains("UHC") ||
text.contains("GBK")
)
}
///|
fn pdf_text_predefined_rksj_single_byte_codepoint(code : Int) -> Int? {
if code >= 0x00 && code <= 0x7F {
Some(code)
} else if code >= 0xA1 && code <= 0xDF {
Some(0xFF61 + code - 0xA1)
} else {
None
}
}
///|
fn pdf_text_predefined_rksj_single_byte_charcode(codepoint : Int) -> Int? {
if codepoint >= 0x00 && codepoint <= 0x7F {
Some(codepoint)
} else if codepoint >= 0xFF61 && codepoint <= 0xFF9F {
Some(0xA1 + codepoint - 0xFF61)
} else {
None
}
}
///|
fn pdf_text_predefined_pair_table_lookup(
table : Array[(Int, Int)],
key : Int,
) -> Int? {
let mut low = 0
let mut high = table.length()
while low < high {
let mid = low + (high - low) / 2
let entry = table[mid]
if key < entry.0 {
high = mid
} else if key > entry.0 {
low = mid + 1
} else {
return Some(entry.1)
}
}
None
}
///|
fn pdf_text_predefined_pair_codepoints_table_lookup(
table : Array[(Int, Array[Int])],
key : Int,
) -> Array[Int]? {
let mut low = 0
let mut high = table.length()
while low < high {
let mid = low + (high - low) / 2
let entry = table[mid]
if key < entry.0 {
high = mid
} else if key > entry.0 {
low = mid + 1
} else {
return Some(entry.1.copy())
}
}
None
}
///|
fn pdf_text_predefined_japan1_direct_codepoint_ranges(
name : PdfName,
) -> Array[(Int, Int, Int)]? {
let text = pdf_text_string_of_name(name)
if text == "/90ms-RKSJ-H" {
Some(pdf_text_japan1_90ms_rksj_codepoint_ranges)
} else if text == "/90pv-RKSJ-H" {
Some(pdf_text_japan1_90pv_rksj_codepoint_ranges)
} else {
None
}
}
///|
fn pdf_text_predefined_japan1_direct_codepoint_sequence_table(
name : PdfName,
) -> Array[(Int, Array[Int])] {
let text = pdf_text_string_of_name(name)
if text == "/90pv-RKSJ-H" {
pdf_text_japan1_90pv_rksj_codepoint_sequence_table
} else {
pdf_text_japan1_90ms_rksj_codepoint_sequence_table
}
}
///|
fn pdf_text_predefined_japan1_direct_charcode_ranges(
name : PdfName,
) -> Array[(Int, Int, Int)]? {
let text = pdf_text_string_of_name(name)
if text == "/90ms-RKSJ-H" {
Some(pdf_text_japan1_90ms_rksj_charcode_ranges)
} else if text == "/90pv-RKSJ-H" {
Some(pdf_text_japan1_90pv_rksj_charcode_ranges)
} else {
None
}
}
///|
fn pdf_text_predefined_japan1_cid_ranges(
name : PdfName,
) -> Array[(Int, Int, Int)]? {
let text = pdf_text_string_of_name(name)
guard pdf_text_predefined_cmap_has_text_orientation(text) else { return None }
if text == "/H" {
Some(pdf_text_japan1_h_cid_ranges)
} else if text == "/V" {
Some(pdf_text_japan1_v_cid_ranges)
} else if text == "/78-H" {
Some(pdf_text_japan1_78_h_cid_ranges)
} else if text == "/78-V" {
Some(pdf_text_japan1_78_v_cid_ranges)
} else if text == "/78-EUC-H" {
Some(pdf_text_japan1_78_euc_h_cid_ranges)
} else if text == "/78-EUC-V" {
Some(pdf_text_japan1_78_euc_v_cid_ranges)
} else if text == "/78-RKSJ-H" {
Some(pdf_text_japan1_78_rksj_h_cid_ranges)
} else if text == "/78-RKSJ-V" {
Some(pdf_text_japan1_78_rksj_v_cid_ranges)
} else if text == "/78ms-RKSJ-H" {
Some(pdf_text_japan1_78ms_rksj_h_cid_ranges)
} else if text == "/78ms-RKSJ-V" {
Some(pdf_text_japan1_78ms_rksj_v_cid_ranges)
} else if text == "/83pv-RKSJ-H" {
Some(pdf_text_japan1_83pv_rksj_h_cid_ranges)
} else if text == "/90ms-RKSJ-H" {
Some(pdf_text_japan1_90ms_rksj_h_cid_ranges)
} else if text == "/90ms-RKSJ-V" {
Some(pdf_text_japan1_90ms_rksj_v_cid_ranges)
} else if text == "/90msp-RKSJ-H" {
Some(pdf_text_japan1_90msp_rksj_h_cid_ranges)
} else if text == "/90msp-RKSJ-V" {
Some(pdf_text_japan1_90msp_rksj_v_cid_ranges)
} else if text == "/90pv-RKSJ-H" {
Some(pdf_text_japan1_90pv_rksj_h_cid_ranges)
} else if text == "/90pv-RKSJ-V" {
Some(pdf_text_japan1_90pv_rksj_v_cid_ranges)
} else if text == "/Add-H" {
Some(pdf_text_japan1_add_h_cid_ranges)
} else if text == "/Add-V" {
Some(pdf_text_japan1_add_v_cid_ranges)
} else if text == "/Add-RKSJ-H" {
Some(pdf_text_japan1_add_rksj_h_cid_ranges)
} else if text == "/Add-RKSJ-V" {
Some(pdf_text_japan1_add_rksj_v_cid_ranges)
} else if text == "/EUC-H" {
Some(pdf_text_japan1_euc_h_cid_ranges)
} else if text == "/EUC-V" {
Some(pdf_text_japan1_euc_v_cid_ranges)
} else if text == "/Ext-H" {
Some(pdf_text_japan1_ext_h_cid_ranges)
} else if text == "/Ext-V" {
Some(pdf_text_japan1_ext_v_cid_ranges)
} else if text == "/Ext-RKSJ-H" {
Some(pdf_text_japan1_ext_rksj_h_cid_ranges)
} else if text == "/Ext-RKSJ-V" {
Some(pdf_text_japan1_ext_rksj_v_cid_ranges)
} else if text == "/Hojo-H" {
Some(pdf_text_japan1_hojo_h_cid_ranges)
} else if text == "/Hojo-V" {
Some(pdf_text_japan1_hojo_v_cid_ranges)
} else if text == "/Hojo-EUC-H" {
Some(pdf_text_japan1_hojo_euc_h_cid_ranges)
} else if text == "/Hojo-EUC-V" {
Some(pdf_text_japan1_hojo_euc_v_cid_ranges)
} else if text == "/NWP-H" {
Some(pdf_text_japan1_nwp_h_cid_ranges)
} else if text == "/NWP-V" {
Some(pdf_text_japan1_nwp_v_cid_ranges)
} else if text == "/RKSJ-H" {
Some(pdf_text_japan1_rksj_h_cid_ranges)
} else if text == "/RKSJ-V" {
Some(pdf_text_japan1_rksj_v_cid_ranges)
} else {
None
}
}
///|
fn pdf_text_predefined_gb1_vertical_codepoint_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("GBK2K") {
Some(pdf_text_gbk2k_vertical_codepoint_table)
} else if text.contains("GBpc-EUC") {
Some(pdf_text_gbpc_euc_vertical_codepoint_table)
} else if text.contains("GBK-EUC") {
Some(pdf_text_gbk_vertical_codepoint_table)
} else if text.contains("GBKp-EUC") {
Some(pdf_text_gbkp_vertical_codepoint_table)
} else if text.contains("GB-EUC") {
Some(pdf_text_gb_euc_vertical_codepoint_table)
} else {
None
}
}
///|
fn pdf_text_predefined_gb1_vertical_charcode_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("GBK2K") {
Some(pdf_text_gbk2k_vertical_charcode_table)
} else if text.contains("GBpc-EUC") {
Some(pdf_text_gbpc_euc_vertical_charcode_table)
} else if text.contains("GBK-EUC") {
Some(pdf_text_gbk_vertical_charcode_table)
} else if text.contains("GBKp-EUC") {
Some(pdf_text_gbkp_vertical_charcode_table)
} else if text.contains("GB-EUC") {
Some(pdf_text_gb_euc_vertical_charcode_table)
} else {
None
}
}
///|
fn pdf_text_predefined_cns1_vertical_codepoint_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("ETenms-B5") {
Some(pdf_text_etenms_b5_vertical_codepoint_table)
} else if text.contains("HKscs-B5") {
Some(pdf_text_hkscs_vertical_codepoint_table)
} else if text.contains("HKdla-B5") {
Some(pdf_text_hkdla_b5_vertical_codepoint_table)
} else if text.contains("HKdlb-B5") {
Some(pdf_text_hkdlb_b5_vertical_codepoint_table)
} else if text.contains("HKgccs-B5") {
Some(pdf_text_hkgccs_b5_vertical_codepoint_table)
} else if text.contains("HKm314-B5") {
Some(pdf_text_hkm314_b5_vertical_codepoint_table)
} else if text.contains("HKm471-B5") {
Some(pdf_text_hkm471_b5_vertical_codepoint_table)
} else if text.contains("B5pc") {
Some(pdf_text_b5pc_vertical_codepoint_table)
} else if text.contains("ETen-B5") {
Some(pdf_text_eten_b5_vertical_codepoint_table)
} else if text.contains("B5") {
Some(pdf_text_big5_vertical_codepoint_table)
} else {
None
}
}
///|
fn pdf_text_predefined_cns1_vertical_charcode_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("ETenms-B5") {
Some(pdf_text_etenms_b5_vertical_charcode_table)
} else if text.contains("HKscs-B5") {
Some(pdf_text_hkscs_vertical_charcode_table)
} else if text.contains("HKdla-B5") {
Some(pdf_text_hkdla_b5_vertical_charcode_table)
} else if text.contains("HKdlb-B5") {
Some(pdf_text_hkdlb_b5_vertical_charcode_table)
} else if text.contains("HKgccs-B5") {
Some(pdf_text_hkgccs_b5_vertical_charcode_table)
} else if text.contains("HKm314-B5") {
Some(pdf_text_hkm314_b5_vertical_charcode_table)
} else if text.contains("HKm471-B5") {
Some(pdf_text_hkm471_b5_vertical_charcode_table)
} else if text.contains("B5pc") {
Some(pdf_text_b5pc_vertical_charcode_table)
} else if text.contains("ETen-B5") {
Some(pdf_text_eten_b5_vertical_charcode_table)
} else if text.contains("B5") {
Some(pdf_text_big5_vertical_charcode_table)
} else {
None
}
}
///|
fn pdf_text_predefined_korea1_vertical_codepoint_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("UHC") {
Some(pdf_text_uhc_vertical_codepoint_table)
} else if text.contains("KSCpc-EUC") {
Some(pdf_text_kscpc_euc_vertical_codepoint_table)
} else if text.contains("KSC-EUC") {
Some(pdf_text_ksc_euc_vertical_codepoint_table)
} else {
None
}
}
///|
fn pdf_text_predefined_korea1_vertical_charcode_table(
name : PdfName,
) -> Array[(Int, Int)]? {
guard pdf_text_predefined_cmap_is_vertical(name) else { return None }
let text = pdf_text_string_of_name(name)
if text.contains("UHC") {
Some(pdf_text_uhc_vertical_charcode_table)
} else if text.contains("KSCpc-EUC") {
Some(pdf_text_kscpc_euc_vertical_charcode_table)
} else if text.contains("KSC-EUC") {
Some(pdf_text_ksc_euc_vertical_charcode_table)
} else {
None
}
}
///|
fn pdf_text_predefined_vertical_codepoint(
table : Array[(Int, Int)]?,
code : Int,
) -> Int? {
match table {
Some(table) => pdf_text_predefined_pair_table_lookup(table, code)
None => None
}
}
///|
fn pdf_text_predefined_vertical_charcode(
table : Array[(Int, Int)]?,
codepoint : Int,
) -> Int? {
match table {
Some(table) => pdf_text_predefined_pair_table_lookup(table, codepoint)
None => None
}
}
///|
fn pdf_text_predefined_cid_range_lookup(
ranges : Array[(Int, Int, Int)],
code : Int,
) -> Int? {
let mut low = 0
let mut high = ranges.length()
while low < high {
let mid = low + (high - low) / 2
let entry = ranges[mid]
if code < entry.0 {
high = mid
} else if code > entry.1 {
low = mid + 1
} else {
return Some(entry.2 + code - entry.0)
}
}
None
}
///|
fn pdf_text_predefined_cid_range_lookup_unsigned(
ranges : ArrayView[(Int, Int, Int)],
code : Int,
) -> Int? {
let target = code.reinterpret_as_uint()
let mut low = 0
let mut high = ranges.length()
while low < high {
let mid = low + (high - low) / 2
let entry = ranges[mid]
if target < entry.0.reinterpret_as_uint() {
high = mid
} else if target > entry.1.reinterpret_as_uint() {
low = mid + 1
} else {
return Some(entry.2 + code - entry.0)
}
}
None
}
///|
fn pdf_text_lower_packed_charcode(current : Int?, candidate : Int) -> Int? {
match current {
Some(value) =>
if candidate.reinterpret_as_uint() < value.reinterpret_as_uint() {
Some(candidate)
} else {
current
}
None => Some(candidate)
}
}
///|
fn pdf_text_lower_optional_packed_charcode(
current : Int?,
candidate : Int?,
) -> Int? {
match candidate {
Some(code) => pdf_text_lower_packed_charcode(current, code)
None => current
}
}
///|
fn pdf_text_predefined_cid_range_charcode_of_cid(
ranges : ArrayView[(Int, Int, Int)],
cid : Int,
) -> Int? {
let mut found : Int? = None
for range in ranges {
let first_cid = range.2
let last_cid = range.2 + range.1 - range.0
if cid >= first_cid && cid <= last_cid {
found = pdf_text_lower_packed_charcode(found, range.0 + cid - first_cid)
}
}
found
}
///|
fn pdf_text_predefined_unicode_table_charcode(
unicode_table : ArrayView[Int],
charcode_ranges : ArrayView[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
guard codepoint != 0 else { return None }
let mut found : Int? = None
for cid, candidate in unicode_table {
if candidate == codepoint {
match
pdf_text_predefined_cid_range_charcode_of_cid(charcode_ranges, cid) {
Some(code) => found = pdf_text_lower_packed_charcode(found, code)
None => ()
}
}
}
found
}
///|
fn pdf_text_predefined_codepoint_range_charcode(
codepoint_ranges : ArrayView[(Int, Int, Int)],
charcode_ranges : ArrayView[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
let mut found : Int? = None
for range in codepoint_ranges {
let first_codepoint = range.2
let last_codepoint = range.2 + range.1 - range.0
if codepoint >= first_codepoint && codepoint <= last_codepoint {
let cid = range.0 + codepoint - first_codepoint
match
pdf_text_predefined_cid_range_charcode_of_cid(charcode_ranges, cid) {
Some(code) => found = pdf_text_lower_packed_charcode(found, code)
None => ()
}
}
}
found
}
///|
fn pdf_text_predefined_sequence_table_charcode(
sequence_table : ArrayView[(Int, Array[Int])],
charcode_ranges : ArrayView[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
let mut found : Int? = None
for entry in sequence_table {
match entry.1 {
[candidate] if candidate == codepoint =>
match
pdf_text_predefined_cid_range_charcode_of_cid(
charcode_ranges,
entry.0,
) {
Some(code) => found = pdf_text_lower_packed_charcode(found, code)
None => ()
}
_ => ()
}
}
found
}
///|
fn pdf_text_japan1_codepoints_of_cid(cid : Int) -> Array[Int]? {
match
pdf_text_predefined_cid_range_lookup(pdf_text_japan1_codepoint_ranges, cid) {
Some(codepoint) => Some([codepoint])
None =>
pdf_text_predefined_pair_codepoints_table_lookup(
pdf_text_japan1_codepoint_sequence_table, cid,
)
}
}
///|
fn pdf_text_predefined_japan1_codepoints(
ranges : Array[(Int, Int, Int)],
code : Int,
) -> Array[Int]? {
match pdf_text_predefined_cid_range_lookup(ranges, code) {
Some(cid) => pdf_text_japan1_codepoints_of_cid(cid)
None => None
}
}
///|
fn pdf_text_predefined_japan1_charcode(
ranges : Array[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
let mut found = pdf_text_predefined_codepoint_range_charcode(
pdf_text_japan1_codepoint_ranges, ranges, codepoint,
)
found = pdf_text_lower_optional_packed_charcode(
found,
pdf_text_predefined_sequence_table_charcode(
pdf_text_japan1_codepoint_sequence_table, ranges, codepoint,
),
)
found
}
///|
fn pdf_text_predefined_japan1_builtin_codepoints(
name : PdfName,
code : Int,
) -> Array[Int]? {
match pdf_text_predefined_japan1_direct_codepoint_ranges(name) {
Some(ranges) =>
match pdf_text_predefined_cid_range_lookup(ranges, code) {
Some(codepoint) => Some([codepoint])
None =>
pdf_text_predefined_pair_codepoints_table_lookup(
pdf_text_predefined_japan1_direct_codepoint_sequence_table(name),
code,
)
}
None =>
match pdf_text_predefined_japan1_cid_ranges(name) {
Some(ranges) => pdf_text_predefined_japan1_codepoints(ranges, code)
None => None
}
}
}
///|
fn pdf_text_predefined_japan1_builtin_charcode(
name : PdfName,
codepoint : Int,
) -> Int? {
match pdf_text_predefined_japan1_direct_charcode_ranges(name) {
Some(ranges) => pdf_text_predefined_cid_range_lookup(ranges, codepoint)
None =>
match pdf_text_predefined_japan1_cid_ranges(name) {
Some(ranges) => pdf_text_predefined_japan1_charcode(ranges, codepoint)
None => None
}
}
}
///|
fn pdf_text_cns1_codepoint_of_cid(cid : Int) -> Int? {
guard cid >= 0 && cid < pdf_text_cns1_unicode_table.length() else {
return None
}
let codepoint = pdf_text_cns1_unicode_table[cid]
if codepoint == 0 {
None
} else {
Some(codepoint)
}
}
///|
fn pdf_text_gb1_codepoint_of_cid(cid : Int) -> Int? {
guard cid >= 0 && cid < pdf_text_gb1_unicode_table.length() else {
return None
}
let codepoint = pdf_text_gb1_unicode_table[cid]
if codepoint == 0 {
None
} else {
Some(codepoint)
}
}
///|
fn pdf_text_predefined_cns1_codepoint(
ranges : Array[(Int, Int, Int)],
code : Int,
) -> Int? {
match pdf_text_predefined_cid_range_lookup(ranges, code) {
Some(cid) => pdf_text_cns1_codepoint_of_cid(cid)
None => None
}
}
///|
fn pdf_text_predefined_cns1_codepoint_unsigned(
ranges : Array[(Int, Int, Int)],
code : Int,
) -> Int? {
match pdf_text_predefined_cid_range_lookup_unsigned(ranges, code) {
Some(cid) => pdf_text_cns1_codepoint_of_cid(cid)
None => None
}
}
///|
fn pdf_text_predefined_cns1_charcode(
ranges : Array[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
pdf_text_predefined_unicode_table_charcode(
pdf_text_cns1_unicode_table, ranges, codepoint,
)
}
///|
fn pdf_text_predefined_cns1_builtin_codepoints(
name : PdfName,
code : Int,
) -> Array[Int]? {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_cns1_vertical_codepoint_table(name),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match pdf_text_predefined_cns1_b5_cid_ranges(name) {
Some(ranges) =>
match pdf_text_predefined_cns1_codepoint(ranges, code) {
Some(codepoint) => Some([codepoint])
None => None
}
None =>
if pdf_text_predefined_cmap_uses_hkscs_charcodes(name) {
match pdf_text_predefined_hkscs_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
} else {
match pdf_text_predefined_cns_euc_cid_ranges(name) {
Some(ranges) =>
match
pdf_text_predefined_cns1_codepoint_unsigned(ranges, code) {
Some(codepoint) => Some([codepoint])
None => None
}
None =>
if pdf_text_predefined_cmap_uses_b5pc_charcodes(name) {
match pdf_text_predefined_b5pc_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
} else if pdf_text_predefined_cmap_uses_big5_charcodes(name) {
match pdf_text_predefined_big5_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
} else {
None
}
}
}
}
}
}
///|
fn pdf_text_predefined_cns1_builtin_charcode(
name : PdfName,
codepoint : Int,
) -> Int? {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_cns1_vertical_charcode_table(name),
codepoint,
) {
Some(code) => Some(code)
None =>
match pdf_text_predefined_cns1_b5_cid_ranges(name) {
Some(ranges) => pdf_text_predefined_cns1_charcode(ranges, codepoint)
None =>
if pdf_text_predefined_cmap_uses_hkscs_charcodes(name) {
pdf_text_predefined_hkscs_charcode(codepoint)
} else {
match pdf_text_predefined_cns_euc_cid_ranges(name) {
Some(ranges) =>
pdf_text_predefined_cns1_charcode(ranges, codepoint)
None =>
if pdf_text_predefined_cmap_uses_b5pc_charcodes(name) {
pdf_text_predefined_b5pc_charcode(codepoint)
} else if pdf_text_predefined_cmap_uses_big5_charcodes(name) {
pdf_text_predefined_big5_charcode(codepoint)
} else {
None
}
}
}
}
}
}
///|
fn pdf_text_valid_unicode_codepoint(codepoint : Int) -> Bool {
codepoint >= 0 &&
codepoint <= 0x10FFFF &&
!(codepoint >= 0xD800 && codepoint <= 0xDFFF)
}
///|
fn pdf_text_packed_charcode_length(code : Int) -> Int {
if code >= 0 && code <= 0xFF {
1
} else if code >= 0 && code <= 0xFFFF {
2
} else if code >= 0 && code <= 0xFFFFFF {
3
} else {
4
}
}
///|
fn pdf_text_packed_charcode_bytes(code : Int, length : Int) -> Bytes {
Bytes::makei(length, fn(index) {
((code >> ((length - index - 1) * 8)) & 0xFF).to_byte()
})
}
///|
fn pdf_text_pack_two_bytes(first : Int, second : Int) -> Int {
(first << 8) | second
}
///|
fn pdf_text_pack_four_bytes(
first : Int,
second : Int,
third : Int,
fourth : Int,
) -> Int {
(((((first << 8) | second) << 8) | third) << 8) | fourth
}
///|
fn pdf_text_pack_bytes_as_charcode(bytes : BytesView) -> Int {
let mut code = 0
for byte in bytes {
code = (code << 8) | byte.to_int()
}
code
}
///|
fn pdf_text_predefined_utf8_codepoints(code : Int) -> Array[Int]? {
let bytes = pdf_text_packed_charcode_bytes(
code,
pdf_text_packed_charcode_length(code),
)
try pdf_codepoints_of_utf8(bytes) catch {
_ => None
} noraise {
codepoints => Some(codepoints)
}
}
///|
fn pdf_text_predefined_utf8_charcode(codepoint : Int) -> Int? {
guard pdf_text_valid_unicode_codepoint(codepoint) else { return None }
if codepoint <= 0x7F {
Some(codepoint)
} else if codepoint <= 0x7FF {
Some(
pdf_text_pack_two_bytes(
0xC0 | (codepoint >> 6),
0x80 | (codepoint & 0x3F),
),
)
} else if codepoint <= 0xFFFF {
Some(
pdf_text_pack_bytes_as_charcode(
Bytes::makei(3, fn(index) {
match index {
0 => (0xE0 | (codepoint >> 12)).to_byte()
1 => (0x80 | ((codepoint >> 6) & 0x3F)).to_byte()
_ => (0x80 | (codepoint & 0x3F)).to_byte()
}
}),
),
)
} else {
Some(
pdf_text_pack_four_bytes(
0xF0 | (codepoint >> 18),
0x80 | ((codepoint >> 12) & 0x3F),
0x80 | ((codepoint >> 6) & 0x3F),
0x80 | (codepoint & 0x3F),
),
)
}
}
///|
fn pdf_text_predefined_utf16_codepoints(code : Int) -> Array[Int]? {
if code >= 0 && code <= 0xFFFF {
if pdf_text_valid_unicode_codepoint(code) {
Some([code])
} else {
None
}
} else if pdf_text_packed_charcode_length(code) == 4 {
let bytes = pdf_text_packed_charcode_bytes(code, 4)
try pdf_codepoints_of_utf16be(bytes) catch {
_ => None
} noraise {
codepoints => Some(codepoints)
}
} else {
None
}
}
///|
fn pdf_text_predefined_utf16_charcode(codepoint : Int) -> Int? {
guard pdf_text_valid_unicode_codepoint(codepoint) else { return None }
if codepoint <= 0xFFFF {
Some(codepoint)
} else {
let shifted = codepoint - 0x10000
let high = 0xD800 | (shifted >> 10)
let low = 0xDC00 | (shifted & 0x3FF)
Some(pdf_text_pack_four_bytes(high >> 8, high & 0xFF, low >> 8, low & 0xFF))
}
}
///|
fn pdf_text_predefined_utf32_codepoints(code : Int) -> Array[Int]? {
if pdf_text_valid_unicode_codepoint(code) {
Some([code])
} else {
None
}
}
///|
fn pdf_text_predefined_utf32_charcode(codepoint : Int) -> Int? {
if pdf_text_valid_unicode_codepoint(codepoint) {
Some(codepoint)
} else {
None
}
}
///|
fn pdf_text_predefined_direct_unicode_codepoints(
name : PdfName,
code : Int,
) -> Array[Int]? {
if pdf_text_predefined_cmap_uses_utf8_charcodes(name) {
pdf_text_predefined_utf8_codepoints(code)
} else if pdf_text_predefined_cmap_uses_utf16_charcodes(name) {
pdf_text_predefined_utf16_codepoints(code)
} else if pdf_text_predefined_cmap_uses_utf32_charcodes(name) {
pdf_text_predefined_utf32_codepoints(code)
} else if pdf_text_predefined_cmap_uses_ucs2_charcodes(name) {
pdf_text_predefined_utf32_codepoints(code)
} else {
None
}
}
///|
fn pdf_text_predefined_direct_unicode_charcode(
name : PdfName,
codepoint : Int,
) -> Int? {
if pdf_text_predefined_cmap_uses_utf8_charcodes(name) {
pdf_text_predefined_utf8_charcode(codepoint)
} else if pdf_text_predefined_cmap_uses_utf16_charcodes(name) {
pdf_text_predefined_utf16_charcode(codepoint)
} else if pdf_text_predefined_cmap_uses_utf32_charcodes(name) {
pdf_text_predefined_utf32_charcode(codepoint)
} else if pdf_text_predefined_cmap_uses_ucs2_charcodes(name) {
if codepoint <= 0xFFFF && pdf_text_valid_unicode_codepoint(codepoint) {
Some(codepoint)
} else {
None
}
} else {
None
}
}
///|
fn pdf_text_predefined_gb1_codepoint(
ranges : Array[(Int, Int, Int)],
code : Int,
) -> Int? {
match pdf_text_predefined_cid_range_lookup(ranges, code) {
Some(cid) => pdf_text_gb1_codepoint_of_cid(cid)
None => None
}
}
///|
fn pdf_text_predefined_gb1_charcode(
ranges : Array[(Int, Int, Int)],
codepoint : Int,
) -> Int? {
pdf_text_predefined_unicode_table_charcode(
pdf_text_gb1_unicode_table, ranges, codepoint,
)
}
///|
fn pdf_text_predefined_gbk2k_codepoint(code : Int) -> Int? {
pdf_text_predefined_gb1_codepoint(pdf_text_gbk2k_cid_ranges, code)
}
///|
fn pdf_text_predefined_gbk2k_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_gb1_charcode(pdf_text_gbk2k_cid_ranges, codepoint)
}
///|
fn pdf_text_predefined_gb_euc_codepoint(code : Int) -> Int? {
if code >= 0x00 && code <= 0x7F {
Some(code)
} else {
pdf_text_predefined_pair_table_lookup(pdf_text_gb_euc_codepoint_table, code)
}
}
///|
fn pdf_text_predefined_gb_euc_charcode(codepoint : Int) -> Int? {
if codepoint >= 0x00 && codepoint <= 0x7F {
Some(codepoint)
} else {
pdf_text_predefined_pair_table_lookup(
pdf_text_gb_euc_charcode_table, codepoint,
)
}
}
///|
fn pdf_text_predefined_gbpc_euc_codepoints(code : Int) -> Array[Int]? {
pdf_text_predefined_pair_codepoints_table_lookup(
pdf_text_gbpc_euc_codepoints_table, code,
)
}
///|
fn pdf_text_predefined_gbpc_euc_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(
pdf_text_gbpc_euc_charcode_table, codepoint,
)
}
///|
fn pdf_text_predefined_big5_codepoint(code : Int) -> Int? {
if code >= 0x00 && code <= 0x7F {
Some(code)
} else {
pdf_text_predefined_pair_table_lookup(pdf_text_big5_codepoint_table, code)
}
}
///|
fn pdf_text_predefined_big5_charcode(codepoint : Int) -> Int? {
if codepoint >= 0x00 && codepoint <= 0x7F {
Some(codepoint)
} else {
pdf_text_predefined_pair_table_lookup(
pdf_text_big5_charcode_table, codepoint,
)
}
}
///|
fn pdf_text_predefined_b5pc_codepoint(code : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(pdf_text_b5pc_codepoint_table, code)
}
///|
fn pdf_text_predefined_b5pc_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(pdf_text_b5pc_charcode_table, codepoint)
}
///|
fn pdf_text_predefined_hkscs_codepoint(code : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(pdf_text_hkscs_codepoint_table, code)
}
///|
fn pdf_text_predefined_hkscs_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(
pdf_text_hkscs_charcode_table, codepoint,
)
}
///|
fn pdf_text_predefined_uhc_codepoint(code : Int) -> Int? {
if code >= 0x00 && code <= 0x7F {
Some(code)
} else {
pdf_text_predefined_pair_table_lookup(pdf_text_uhc_codepoint_table, code)
}
}
///|
fn pdf_text_predefined_uhc_charcode(codepoint : Int) -> Int? {
if codepoint >= 0x00 && codepoint <= 0x7F {
Some(codepoint)
} else {
pdf_text_predefined_pair_table_lookup(
pdf_text_uhc_charcode_table, codepoint,
)
}
}
///|
fn pdf_text_predefined_ksc_euc_codepoint(code : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(pdf_text_ksc_euc_codepoint_table, code)
}
///|
fn pdf_text_predefined_ksc_euc_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(
pdf_text_ksc_euc_charcode_table, codepoint,
)
}
///|
fn pdf_text_predefined_kscpc_euc_codepoints(code : Int) -> Array[Int]? {
pdf_text_predefined_pair_codepoints_table_lookup(
pdf_text_kscpc_euc_codepoints_table, code,
)
}
///|
fn pdf_text_predefined_kscpc_euc_charcode(codepoint : Int) -> Int? {
pdf_text_predefined_pair_table_lookup(
pdf_text_kscpc_euc_charcode_table, codepoint,
)
}
///|
fn pdf_text_predefined_gbk_codepoint(code : Int) -> Int? {
if code >= 0x00 && code <= 0x80 {
Some(code)
} else if code == 0xFF {
Some(0xF8F5)
} else {
pdf_text_predefined_pair_table_lookup(pdf_text_gbk_codepoint_table, code)
}
}
///|
fn pdf_text_predefined_gbk_charcode(codepoint : Int) -> Int? {
if codepoint >= 0x00 && codepoint <= 0x80 {
Some(codepoint)
} else if codepoint == 0xF8F5 {
Some(0xFF)
} else {
pdf_text_predefined_pair_table_lookup(
pdf_text_gbk_charcode_table, codepoint,
)
}
}
///|
/// Return true when this CMap consumes text as fixed two-byte character codes.
///
/// Identity CMaps and common UCS2/UTF16 predefined maps are treated as
/// two-byte. Parsed external CMaps are two-byte only when all code spaces have
/// length 2, or when they inherit an identity base with no explicit spaces.
pub fn PdfCMapEncoding::uses_two_byte_codes(self : PdfCMapEncoding) -> Bool {
match self {
PdfPredefinedCMap(name) =>
self.is_identity_h() ||
self.is_identity_v() ||
pdf_text_predefined_cmap_uses_two_byte_charcodes(name)
PdfExternalCMap(_, parsed) =>
if parsed.codespaces.length() == 0 {
match parsed.usecmap {
Some(name) =>
name == pdf_text_identity_h_name ||
name == pdf_text_identity_v_name ||
pdf_text_predefined_cmap_uses_two_byte_charcodes(name)
None => false
}
} else {
for codespace in parsed.codespaces {
if codespace.length != 2 {
break false
}
} nobreak {
true
}
}
_ => false
}
}
///|
fn pdf_text_parsed_cmap_codespace_charcode(
codespace : PdfCMapCodeSpace,
text : BytesView,
index : Int,
) -> Int? {
guard codespace.length > 0 && index + codespace.length <= text.length() else {
return None
}
let mut code = 0
for offset in 0..= codespace.first && code <= codespace.last {
Some(code)
} else {
None
}
}
///|
fn pdf_text_parsed_cmap_next_charcode(
parsed : PdfParsedCMap,
text : BytesView,
index : Int,
) -> (Int, Int)? {
let mut best : (Int, Int)? = None
for codespace in parsed.codespaces {
match pdf_text_parsed_cmap_codespace_charcode(codespace, text, index) {
Some(code) =>
match best {
Some((_, length)) if length >= codespace.length => ()
_ => best = Some((code, codespace.length))
}
None => ()
}
}
best
}
///|
fn pdf_text_identity_codespace() -> PdfCMapCodeSpace {
{ length: 2, first: 0x0000, last: 0xFFFF }
}
///|
fn pdf_text_parsed_cmap_has_identity_base(parsed : PdfParsedCMap) -> Bool {
match parsed.usecmap {
Some(name) => {
let encoding = PdfPredefinedCMap(name)
encoding.is_identity_h() || encoding.is_identity_v()
}
None => false
}
}
///|
fn pdf_text_parsed_cmap_predefined_base(parsed : PdfParsedCMap) -> PdfName? {
match parsed.usecmap {
Some(name) if !pdf_text_parsed_cmap_has_identity_base(parsed) => Some(name)
_ => None
}
}
///|
fn pdf_text_parsed_cmap_identity_charcode(
parsed : PdfParsedCMap,
text : BytesView,
index : Int,
) -> (Int, Int)? {
guard pdf_text_parsed_cmap_has_identity_base(parsed) else { return None }
match
pdf_text_parsed_cmap_codespace_charcode(
pdf_text_identity_codespace(),
text,
index,
) {
Some(code) => Some((code, 2))
None => None
}
}
///|
fn pdf_text_parsed_cmap_charcodes_of_text(
parsed : PdfParsedCMap,
text : BytesView,
) -> Array[Int] raise PdfError {
guard parsed.codespaces.length() > 0 ||
pdf_text_parsed_cmap_has_identity_base(parsed) else {
match pdf_text_parsed_cmap_predefined_base(parsed) {
Some(name) =>
return pdf_text_predefined_cmap_charcodes_of_text(name, text)
None => return [ for byte in text => byte.to_int() ]
}
}
let output : Array[Int] = []
let mut index = 0
while index < text.length() {
let next = match pdf_text_parsed_cmap_next_charcode(parsed, text, index) {
Some((local_code, length)) =>
match pdf_text_parsed_cmap_identity_charcode(parsed, text, index) {
Some((identity_code, identity_length)) if identity_length > length =>
Some((identity_code, identity_length))
_ => Some((local_code, length))
}
None => pdf_text_parsed_cmap_identity_charcode(parsed, text, index)
}
match next {
Some((code, length)) => {
output.push(code)
index += length
}
None => raise BadText
}
}
output
}
///|
/// Test whether this Type 0 font uses `/Identity-H`.
pub fn PdfCIDKeyedFont::is_identity_h(self : PdfCIDKeyedFont) -> Bool {
self.encoding.is_identity_h()
}
///|
/// Test whether this Type 0 font uses `/Identity-V`.
pub fn PdfCIDKeyedFont::is_identity_v(self : PdfCIDKeyedFont) -> Bool {
self.encoding.is_identity_v()
}
///|
/// Return true when this Type 0 font uses fixed two-byte character codes.
pub fn PdfCIDKeyedFont::uses_two_byte_codes(self : PdfCIDKeyedFont) -> Bool {
self.encoding.uses_two_byte_codes()
}
///|
/// Return a human-readable simple-font subtype label.
///
/// Type 3 labels include the declared CharProc names to make debugging parsed
/// glyph programs easier.
pub fn PdfSimpleFontType::debug_name(self : PdfSimpleFontType) -> String {
match self {
PdfType1 => "Type 1"
PdfMMType1 => "MM Type 1"
PdfType3(data) => {
let mut text = "Type 3: charprocs for"
for entry in data.charprocs {
let (name, _) = entry
text = text + pdf_text_string_of_name(name)
}
text
}
PdfTrueType => "Truetype"
}
}
///|
/// Return a multi-line debug summary for this simple font.
pub fn PdfSimpleFont::debug_name(self : PdfSimpleFont) -> String {
let basefont = match self.basefont {
Some(name) => pdf_text_string_of_name(name)
None => ""
}
"fonttype = " +
self.fonttype.debug_name() +
"\nbasefont " +
basefont +
"\nencoding is " +
self.encoding.debug_name() +
"\n"
}
///|
/// One `/Differences` entry in a simple-font encoding dictionary.
///
/// `code` is the one-byte character code that maps to `name`.
pub(all) struct PdfEncodingDifference {
name : PdfName
code : Int
} derive(Debug, Eq, ToJson)
///|
/// Simple-font character encoding.
///
/// `PdfCustomEncoding` layers `/Differences` over a base encoding.
/// `PdfFillUndefinedWithStandard` models TrueType behavior where undefined
/// entries fall back to StandardEncoding.
pub(all) enum PdfEncoding {
PdfImplicitInFontFile
PdfStandardEncoding
PdfMacRomanEncoding
PdfWinAnsiEncoding
PdfMacExpertEncoding
PdfCustomEncoding(PdfEncoding, Array[PdfEncodingDifference])
PdfFillUndefinedWithStandard(PdfEncoding)
} derive(Debug, Eq, ToJson)
///|
/// Parsed font model used by text extraction and font writing.
pub(all) enum PdfFont {
PdfFontStandard(PdfStandardFontData)
PdfFontSimple(PdfSimpleFont)
PdfFontCIDKeyed(PdfCIDKeyedFont)
} derive(Debug, Eq, ToJson)
///|
/// Text extractor bound to a parsed font.
///
/// The extractor converts PDF text-string bytes to character codes, glyph
/// names, and Unicode codepoints according to the font's encoding data.
pub(all) struct PdfTextExtractor {
font : PdfFont
} derive(Debug, Eq, ToJson)
///|
/// Extracted glyph result for one character code.
///
/// `glyphname` is the resolved PDF glyph name and `codepoints` is the Unicode
/// scalar sequence inferred from ToUnicode, CMap, or Adobe glyph-list data.
pub(all) struct PdfTextGlyph {
glyphname : PdfName
codepoints : Array[Int]
} derive(Debug, Eq, ToJson)
///|
/// Return a human-readable label for a parsed font.
pub fn PdfFont::debug_name(self : PdfFont) -> String {
match self {
PdfFontStandard(font) => font.debug_name()
PdfFontSimple(font) => "SimpleFont " + font.debug_name()
PdfFontCIDKeyed(font) => font.debug_name()
}
}
///|
/// Compatibility wrapper for `PdfFont::debug_name`.
pub fn pdf_string_of_font(font : PdfFont) -> String {
font.debug_name()
}
///|
/// Test whether this font is a Type 0 font using `/Identity-H`.
pub fn PdfFont::is_identity_h(self : PdfFont) -> Bool {
match self {
PdfFontCIDKeyed(font) => font.is_identity_h()
_ => false
}
}
///|
/// Compatibility wrapper for `PdfFont::is_identity_h`.
pub fn pdf_is_identity_h(font : PdfFont) -> Bool {
font.is_identity_h()
}
///|
/// Test whether this font is a Type 0 font using `/Identity-V`.
pub fn PdfFont::is_identity_v(self : PdfFont) -> Bool {
match self {
PdfFontCIDKeyed(font) => font.is_identity_v()
_ => false
}
}
///|
/// Return true when this font consumes fixed two-byte text character codes.
pub fn PdfFont::uses_two_byte_codes(self : PdfFont) -> Bool {
match self {
PdfFontCIDKeyed(font) => font.uses_two_byte_codes()
_ => false
}
}
///|
/// Build a text extractor for an already parsed font.
pub fn PdfFont::text_extractor(self : PdfFont) -> PdfTextExtractor {
{ font: self }
}
///|
/// Compatibility wrapper for `PdfFont::text_extractor`.
pub fn pdf_text_extractor_of_font_real(font : PdfFont) -> PdfTextExtractor {
font.text_extractor()
}
///|
/// Build a pure reverse lookup closure for an already parsed font.
///
/// The returned closure maps one Unicode codepoint to the first matching PDF
/// character code when the font can represent it. `debug` is accepted for
/// CamlPDF API compatibility; this implementation does not write diagnostics.
pub fn pdf_charcode_extractor_of_font_real(
font : PdfFont,
debug? : Bool = false,
) -> (Int) -> Int? {
// CamlPDF reports missing glyphs to stderr when debug is true; this wrapper
// keeps the lookup pure while preserving the API shape.
ignore(debug)
let extractor = font.text_extractor()
fn(codepoint) { extractor.charcode_of_codepoint(codepoint) }
}
///|
fn pdf_text_width_of_standard_charcode(
font : PdfStandardFont,
encoding : PdfEncoding,
code : Int,
) -> Double {
if code >= 0 && code <= 255 {
let bytes : FixedArray[Byte] = [code.to_byte()]
font.text_width(encoding, Bytes::from_array(bytes)).to_double()
} else {
0.0
}
}
///|
fn pdf_text_simple_font_charcode_width(
font : PdfSimpleFont,
code : Int,
) -> Double {
match font.fontmetrics {
Some(metrics) =>
if code >= 0 && code < metrics.length() {
metrics[code]
} else {
0.0
}
None =>
match font.basefont {
Some(basefont) =>
match pdf_standard_font_of_pdf_name(basefont) {
Some(standard_font) =>
pdf_text_width_of_standard_charcode(
standard_font,
font.encoding,
code,
)
None => 0.0
}
None => 0.0
}
}
}
///|
fn pdf_text_cid_font_charcode_width(
font : PdfCIDKeyedFont,
code : Int,
) -> Double {
for entry in font.composite.cid_widths {
if entry.0 == code {
break entry.1
}
} nobreak {
font.composite.cid_default_width
}
}
///|
/// Measure PDF text bytes in glyph-space units for this extractor's font.
///
/// Text bytes are segmented according to the font encoding. Malformed byte
/// sequences raise `PdfError`, and missing metrics contribute width `0`.
pub fn PdfTextExtractor::text_width(
self : PdfTextExtractor,
text : BytesView,
) -> Double raise PdfError {
match self.font {
PdfFontStandard(font) => font.text_width(text).to_double()
PdfFontSimple(font) => {
let mut width = 0.0
for code in self.font.pdf_text_charcodes_of_text(text) {
width += pdf_text_simple_font_charcode_width(font, code)
}
width
}
PdfFontCIDKeyed(font) => {
let mut width = 0.0
for code in self.font.pdf_text_charcodes_of_text(text) {
width += pdf_text_cid_font_charcode_width(font, code)
}
width
}
}
}
///|
/// Return a human-readable encoding label.
pub fn PdfEncoding::debug_name(self : PdfEncoding) -> String {
match self {
PdfImplicitInFontFile => "ImplicitInFontFile"
PdfStandardEncoding => "StandardEncoding"
PdfMacRomanEncoding => "MacRomanEncoding"
PdfWinAnsiEncoding => "WinAnsiEncoding"
PdfMacExpertEncoding => "MacExpertEncoding"
PdfCustomEncoding(base, differences) => {
let mut text = "CustomEncoding with base " +
base.debug_name() +
" and differences "
for difference in differences {
text = text +
difference.code.to_string() +
" -> " +
pdf_text_string_of_name(difference.name) +
", "
}
text
}
PdfFillUndefinedWithStandard(base) =>
"FillUndefinedWithStandard " + base.debug_name()
}
}
///|
/// Return the PDF name for a built-in simple-font encoding.
///
/// Custom, implicit, and fallback encodings do not have a direct PDF name and
/// return `None`.
pub fn PdfEncoding::pdf_name(self : PdfEncoding) -> PdfName? {
match self {
PdfStandardEncoding => Some(pdf_text_standard_encoding_name)
PdfMacRomanEncoding => Some(pdf_text_mac_roman_encoding_name)
PdfWinAnsiEncoding => Some(pdf_text_win_ansi_encoding_name)
PdfMacExpertEncoding => Some(pdf_text_mac_expert_encoding_name)
_ => None
}
}
///|
/// Recognize a built-in simple-font encoding name.
pub fn pdf_encoding_of_name(name : PdfName) -> PdfEncoding? {
match name {
name if name == pdf_text_standard_encoding_name => Some(PdfStandardEncoding)
name if name == pdf_text_mac_roman_encoding_name =>
Some(PdfMacRomanEncoding)
name if name == pdf_text_win_ansi_encoding_name => Some(PdfWinAnsiEncoding)
name if name == pdf_text_mac_expert_encoding_name =>
Some(PdfMacExpertEncoding)
_ => None
}
}
///|
fn pdf_text_dictionary_has_key(object : PdfObject, key : PdfName) -> Bool {
match object.dictionary_view() {
Some(entries) =>
for entry in entries {
let (name, _) = entry
if name == key {
break true
}
} nobreak {
false
}
None => false
}
}
///|
fn pdf_text_find_immediate_indirect(object : PdfObject, key : PdfName) -> Int? {
match object.dictionary_view() {
Some(entries) =>
for entry in entries {
let (name, value) = entry
if name == key {
break match value {
PdfIndirect(number) => Some(number)
_ => None
}
}
} nobreak {
None
}
None => None
}
}
///|
fn pdf_text_fontfile_of_descriptor(descriptor : PdfObject) -> PdfFontFile? {
match
pdf_text_find_immediate_indirect(descriptor, pdf_text_font_file_key_name) {
Some(number) => Some(PdfFontFile(number))
None =>
match
pdf_text_find_immediate_indirect(
descriptor, pdf_text_font_file2_key_name,
) {
Some(number) => Some(PdfFontFile2(number))
None =>
match
pdf_text_find_immediate_indirect(
descriptor, pdf_text_font_file3_key_name,
) {
Some(number) => Some(PdfFontFile3(number))
None => None
}
}
}
}
///|
fn pdf_text_zero_rectangle() -> PdfRectangle {
{ min_x: 0.0, min_y: 0.0, max_x: 0.0, max_y: 0.0 }
}
///|
fn pdf_text_empty_font_descriptor() -> PdfFontDescriptor {
{
ascent: 0.0,
descent: 0.0,
avgwidth: 0.0,
maxwidth: 0.0,
flags: 0,
fontbbox: pdf_text_zero_rectangle(),
italicangle: 0.0,
capheight: 0.0,
xheight: 0.0,
stemv: 0.0,
fontfile: None,
charset: None,
tounicode: None,
}
}
///|
fn PdfDocument::pdf_text_optional_number(
self : PdfDocument,
key : PdfName,
object : PdfObject,
) -> Double raise PdfError {
match self.lookup_direct(key, object) {
Some(value) => self.get_number(value)
None => 0.0
}
}
///|
fn PdfDocument::pdf_text_optional_integer(
self : PdfDocument,
key : PdfName,
object : PdfObject,
) -> Int raise PdfError {
match self.lookup_direct(key, object) {
Some(value) => self.get_number(value).to_int()
None => 0
}
}
///|
fn pdf_text_parse_charset(bytes : BytesView) -> Array[PdfName] raise PdfError {
let cursor = byte_cursor_of_view(bytes)
let names : Array[PdfName] = []
let mut done = false
while !done {
cursor.drop_pdf_whitespace()
match cursor.lex_pdf_name() {
LexName(name) =>
if name == pdf_text_slash_name {
done = true
} else {
names.push(name)
}
_ => done = true
}
}
names
}
///|
fn PdfDocument::pdf_text_font_charset(
self : PdfDocument,
descriptor : PdfObject,
) -> Array[PdfName]? raise PdfError {
match self.lookup_direct(pdf_text_charset_key_name, descriptor) {
Some(PdfString(bytes)) => Some(pdf_text_parse_charset(bytes))
_ => None
}
}
///|
/// Read the `/FontDescriptor` dictionary attached to a font.
///
/// Missing descriptors return `None`. Present descriptors are parsed
/// tolerantly for optional numeric fields, while malformed required shapes
/// such as an invalid `/FontBBox` still raise through the underlying object
/// readers.
pub fn PdfDocument::read_font_descriptor(
self : PdfDocument,
font : PdfObject,
) -> PdfFontDescriptor? raise PdfError {
match self.lookup_direct(pdf_text_font_descriptor_key_name, font) {
None => None
Some(descriptor) => {
let fontbbox = match
self.lookup_direct(pdf_text_font_bbox_key_name, descriptor) {
Some(value) => self.parse_rectangle(value)
None => pdf_text_zero_rectangle()
}
Some({
..pdf_text_empty_font_descriptor(),
ascent: self.pdf_text_optional_number(
pdf_text_ascent_key_name, descriptor,
),
descent: self.pdf_text_optional_number(
pdf_text_descent_key_name, descriptor,
),
avgwidth: self.pdf_text_optional_number(
pdf_text_avg_width_key_name, descriptor,
),
maxwidth: self.pdf_text_optional_number(
pdf_text_max_width_key_name, descriptor,
),
fontbbox,
flags: self.pdf_text_optional_integer(
pdf_text_flags_key_name, descriptor,
),
italicangle: self.pdf_text_optional_number(
pdf_text_italic_angle_key_name, descriptor,
),
capheight: self.pdf_text_optional_number(
pdf_text_cap_height_key_name, descriptor,
),
xheight: self.pdf_text_optional_number(
pdf_text_xheight_key_name, descriptor,
),
stemv: self.pdf_text_optional_number(
pdf_text_stemv_key_name, descriptor,
),
fontfile: pdf_text_fontfile_of_descriptor(descriptor),
charset: self.pdf_text_font_charset(descriptor),
})
}
}
}
///|
fn PdfDocument::pdf_text_font_metrics_descriptor(
self : PdfDocument,
font : PdfObject,
) -> PdfObject? {
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) if subtype == pdf_text_type3_name => Some(font)
_ => self.lookup_direct(pdf_text_font_descriptor_key_name, font)
}
}
///|
fn PdfDocument::pdf_text_font_char_bound(
self : PdfDocument,
font : PdfObject,
key : PdfName,
error : PdfError,
) -> Int raise PdfError {
match self.lookup_direct(key, font) {
Some(PdfInteger(value)) if value >= 0 && value <= 255 => value
_ => raise error
}
}
///|
fn PdfDocument::pdf_text_font_missing_width(
self : PdfDocument,
descriptor : PdfObject,
) -> Double raise PdfError {
match self.lookup_direct(pdf_text_missing_width_key_name, descriptor) {
Some(value) => self.get_number(value)
None => 0.0
}
}
///|
fn PdfDocument::pdf_text_font_widths_array(
self : PdfDocument,
font : PdfObject,
) -> Array[PdfObject] raise PdfError {
match self.lookup_direct(pdf_text_widths_key_name, font) {
Some(PdfArray(values)) => values
_ => raise FontWidthsExpected
}
}
///|
/// Read normalized one-byte font metrics for a simple or Type 3 font.
///
/// The result contains 256 entries when `/Widths`, `/FirstChar`, and
/// `/LastChar` are present and well formed. Missing metrics return `None`;
/// malformed bounds or width arrays raise the corresponding font error.
pub fn PdfDocument::read_font_metrics(
self : PdfDocument,
font : PdfObject,
) -> Array[Double]? raise PdfError {
match self.pdf_text_font_metrics_descriptor(font) {
None => None
Some(descriptor) => {
let firstchar = self.pdf_text_font_char_bound(
font,
pdf_text_first_char_key_name,
FontFirstCharExpected,
)
let lastchar = self.pdf_text_font_char_bound(
font,
pdf_text_last_char_key_name,
FontLastCharExpected,
)
guard lastchar >= firstchar else { raise FontWidthsExpected }
let widths = self.pdf_text_font_widths_array(font)
guard widths.length() == lastchar - firstchar + 1 else {
raise FontWidthsExpected
}
let missingwidth = self.pdf_text_font_missing_width(descriptor)
let metrics : Array[Double] = []
for _ in 0.. raise FontWidthExpected
},
)
}
for _ in 0..<(255 - lastchar) {
metrics.push(missingwidth)
}
Some(metrics)
}
}
}
///|
fn PdfDocument::pdf_text_read_type3_glyphs(
self : PdfDocument,
font : PdfObject,
) -> PdfType3Glyphs raise PdfError {
let fontbbox = match self.lookup_direct(pdf_text_font_bbox_key_name, font) {
Some(value) =>
self.parse_rectangle(value) catch {
_ => pdf_text_zero_rectangle()
}
None => pdf_text_zero_rectangle()
}
let charprocs = match self.lookup_direct(pdf_text_charprocs_key_name, font) {
Some(PdfDictionary(entries)) => entries
_ => raise FontCharProcsExpected
}
let resources = match self.lookup_direct(pdf_text_resources_key_name, font) {
Some(value) => value
None => PdfDictionary([])
}
{
fontbbox,
fontmatrix: self.parse_matrix(pdf_text_font_matrix_key_name, font),
charprocs,
resources,
}
}
///|
fn PdfDocument::pdf_text_simple_font_type_of_name(
self : PdfDocument,
font : PdfObject,
subtype : PdfName,
) -> PdfSimpleFontType? raise PdfError {
if subtype == pdf_text_type1_name {
Some(PdfType1)
} else if subtype == pdf_text_mmtype1_name {
Some(PdfMMType1)
} else if subtype == pdf_text_type3_name {
Some(PdfType3(self.pdf_text_read_type3_glyphs(font)))
} else if subtype == pdf_text_true_type_name_value {
Some(PdfTrueType)
} else {
None
}
}
///|
fn PdfDocument::pdf_text_read_basefont(
self : PdfDocument,
font : PdfObject,
) -> PdfName? {
match self.lookup_direct(pdf_text_base_font_key_name, font) {
Some(PdfNameObject(name)) => Some(name)
_ => None
}
}
///|
/// Parse a simple-font dictionary.
///
/// Supported subtypes are Type1, MMType1, Type3, and TrueType. The returned
/// value includes optional descriptors, metrics, Type 3 CharProc data, and the
/// resolved simple-font encoding.
pub fn PdfDocument::read_simple_font(
self : PdfDocument,
font : PdfObject,
) -> PdfSimpleFont raise PdfError {
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) =>
match self.pdf_text_simple_font_type_of_name(font, subtype) {
Some(fonttype) =>
{
fonttype,
basefont: self.pdf_text_read_basefont(font),
firstchar: 0,
lastchar: 0,
widths: [],
fontdescriptor: self.read_font_descriptor(font),
fontmetrics: self.read_font_metrics(font),
encoding: self.read_encoding(font),
}
None => raise FontSubtypeExpected
}
_ => raise FontSubtypeExpected
}
}
///|
fn PdfDocument::pdf_text_font_is_embedded(
self : PdfDocument,
font : PdfObject,
) -> Bool {
match self.lookup_direct(pdf_text_font_descriptor_key_name, font) {
Some(descriptor) =>
pdf_text_dictionary_has_key(descriptor, pdf_text_font_file_key_name) ||
pdf_text_dictionary_has_key(descriptor, pdf_text_font_file2_key_name) ||
pdf_text_dictionary_has_key(descriptor, pdf_text_font_file3_key_name)
None => false
}
}
///|
fn PdfDocument::pdf_text_font_is_symbolic(
self : PdfDocument,
font : PdfObject,
) -> Bool raise PdfError {
match self.lookup_direct(pdf_text_font_descriptor_key_name, font) {
Some(descriptor) =>
match self.lookup_direct(pdf_text_flags_key_name, descriptor) {
Some(PdfInteger(flags)) => (flags & (1 << 3)) > 0
_ => raise FontFlagsExpected
}
None => false
}
}
///|
fn PdfDocument::pdf_text_default_base_encoding(
self : PdfDocument,
font : PdfObject,
) -> PdfEncoding raise PdfError {
if self.pdf_text_font_is_embedded(font) ||
self.pdf_text_font_is_symbolic(font) {
PdfImplicitInFontFile
} else {
PdfStandardEncoding
}
}
///|
fn PdfDocument::read_encoding_base(
self : PdfDocument,
encoding_dictionary : PdfObject,
font : PdfObject,
) -> PdfEncoding raise PdfError {
match
self.lookup_direct(pdf_text_base_encoding_key_name, encoding_dictionary) {
Some(PdfNameObject(name)) =>
match pdf_encoding_of_name(name) {
Some(encoding) => encoding
None => raise EncodingExpected
}
Some(_) => raise EncodingExpected
None => self.pdf_text_default_base_encoding(font)
}
}
///|
fn PdfDocument::read_encoding_differences(
self : PdfDocument,
differences : PdfObject,
) -> Array[PdfEncodingDifference] raise PdfError {
match self.direct(differences) {
PdfArray(values) => {
let output : Array[PdfEncodingDifference] = []
let mut next_code : Int? = None
for value in values {
match self.direct(value) {
PdfInteger(code) => next_code = Some(code)
PdfNameObject(name) =>
match next_code {
Some(code) => {
output.push({ name, code })
next_code = Some(code + 1)
}
None => raise EncodingDifferencesMalformed
}
_ => raise EncodingDifferencesMalformed
}
}
output
}
_ => raise EncodingDifferencesMalformed
}
}
///|
fn pdf_text_is_true_type_name(name : PdfName) -> Bool {
name == pdf_text_true_type_name_value
}
///|
fn pdf_text_is_simple_font_subtype_name(name : PdfName) -> Bool {
name == pdf_text_type1_name ||
name == pdf_text_mmtype1_name ||
name == pdf_text_type3_name ||
name == pdf_text_true_type_name_value
}
///|
fn pdf_text_is_standard14_subtype_name(name : PdfName) -> Bool {
name == pdf_text_type1_name || name == pdf_text_true_type_name_value
}
///|
/// Read the simple-font encoding from a font dictionary.
///
/// Name encodings are recognized directly. Encoding dictionaries combine
/// `/BaseEncoding` and `/Differences`; TrueType encodings additionally fall
/// back to StandardEncoding for undefined entries. Missing or unrecognized
/// encodings use `PdfImplicitInFontFile`.
pub fn PdfDocument::read_encoding(
self : PdfDocument,
font : PdfObject,
) -> PdfEncoding raise PdfError {
match self.lookup_direct(pdf_text_encoding_key_name, font) {
Some(PdfNameObject(name)) =>
match pdf_encoding_of_name(name) {
Some(encoding) => encoding
None => PdfImplicitInFontFile
}
Some(PdfDictionary(_) as encoding_dictionary) =>
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) if pdf_text_is_simple_font_subtype_name(
subtype,
) => {
let base = self.read_encoding_base(encoding_dictionary, font)
let encoding = match
self.lookup_direct(
pdf_text_differences_key_name, encoding_dictionary,
) {
Some(differences) =>
PdfCustomEncoding(
base,
self.read_encoding_differences(differences),
)
None => base
}
if pdf_text_is_true_type_name(subtype) {
PdfFillUndefinedWithStandard(encoding)
} else {
encoding
}
}
_ => raise FontSubtypeExpected
}
Some(_) => PdfImplicitInFontFile
None => PdfImplicitInFontFile
}
}
///|
/// Return true if a font dictionary is an unembedded standard 14 font.
///
/// A matching Type1 or TrueType `/BaseFont` without explicit `/Widths` is
/// treated as a standard-font dictionary.
pub fn PdfDocument::is_standard14_font(
self : PdfDocument,
font : PdfObject,
) -> Bool {
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) if pdf_text_is_standard14_subtype_name(subtype) =>
match self.lookup_direct(pdf_text_base_font_key_name, font) {
Some(PdfNameObject(base_font)) =>
pdf_standard_font_of_pdf_name(base_font) != None &&
self.lookup_direct(pdf_text_widths_key_name, font) == None
_ => false
}
_ => false
}
}
///|
/// Return true if a font dictionary has a simple-font subtype.
pub fn PdfDocument::is_simple_font(
self : PdfDocument,
font : PdfObject,
) -> Bool {
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) =>
pdf_text_is_simple_font_subtype_name(subtype)
_ => false
}
}
///|
/// Return true if a font dictionary is a Type 0 CID-keyed font.
pub fn PdfDocument::is_cidkeyed_font(
self : PdfDocument,
font : PdfObject,
) -> Bool {
match self.lookup_direct(pdf_text_subtype_key_name, font) {
Some(PdfNameObject(subtype)) => subtype == pdf_text_type0_name
_ => false
}
}
///|
fn PdfDocument::pdf_text_cid_string_entry(
self : PdfDocument,
dictionary : PdfObject,
key : PdfName,
error : PdfError,
) -> PdfBytes raise PdfError {
match self.lookup_direct(key, dictionary) {
Some(PdfString(bytes)) => bytes
_ => raise error
}
}
///|
/// Read a CID-system-info dictionary.
///
/// Registry and ordering are returned as byte strings, matching PDF string
/// semantics. Missing or malformed required fields raise `PdfError`.
pub fn PdfDocument::read_cid_system_info(
self : PdfDocument,
dictionary : PdfObject,
) -> PdfCIDSystemInfo raise PdfError {
{
registry: self.pdf_text_cid_string_entry(
dictionary,
pdf_text_registry_key_name,
CIDRegistryExpected,
),
ordering: self.pdf_text_cid_string_entry(
dictionary,
pdf_text_ordering_key_name,
CIDOrderingExpected,
),
supplement: match
self.lookup_direct(pdf_text_supplement_key_name, dictionary) {
Some(PdfInteger(value)) => value
_ => raise CIDSupplementExpected
},
}
}
///|
fn PdfDocument::pdf_text_cid_number(
self : PdfDocument,
value : PdfObject,
error : PdfError,
) -> Double raise PdfError {
self.get_number(value) catch {
_ => raise error
}
}
///|
fn PdfDocument::pdf_text_read_cid_widths(
self : PdfDocument,
values : ArrayView[PdfObject],
) -> Array[(Int, Double)] raise PdfError {
let output : Array[(Int, Double)] = []
let mut index = 0
while index < values.length() {
match self.direct(values[index]) {
PdfInteger(first_code) => {
guard index + 1 < values.length() else { raise CIDWidthsExpected }
match self.direct(values[index + 1]) {
PdfArray(widths) => {
for offset in 0.. {
guard index + 2 < values.length() && last_code >= first_code else {
raise CIDWidthsExpected
}
let width = self.pdf_text_cid_number(
values[index + 2],
CIDWidthsExpected,
)
for code in first_code..<=last_code {
output.push((code, width))
}
index += 3
}
_ => raise CIDWidthsExpected
}
}
_ => raise CIDWidthsExpected
}
}
output
}
///|
fn PdfDocument::pdf_text_read_cid_widths2(
self : PdfDocument,
values : ArrayView[PdfObject],
) -> Array[(Int, PdfCIDVerticalWidth)] raise PdfError {
let output : Array[(Int, PdfCIDVerticalWidth)] = []
let mut index = 0
while index < values.length() {
match self.direct(values[index]) {
PdfInteger(first_code) => {
guard index + 1 < values.length() else { raise CIDWidths2Expected }
match self.direct(values[index + 1]) {
PdfArray(widths) => {
guard widths.length() % 3 == 0 else { raise CIDWidths2Expected }
let mut code = first_code
let mut width_index = 0
while width_index < widths.length() {
output.push(
(
code,
{
width: self.pdf_text_cid_number(
widths[width_index],
CIDWidths2Expected,
),
vx: self.pdf_text_cid_number(
widths[width_index + 1],
CIDWidths2Expected,
),
vy: self.pdf_text_cid_number(
widths[width_index + 2],
CIDWidths2Expected,
),
},
),
)
code += 1
width_index += 3
}
index += 2
}
PdfInteger(last_code) => {
guard index + 4 < values.length() && last_code >= first_code else {
raise CIDWidths2Expected
}
let width = {
width: self.pdf_text_cid_number(
values[index + 2],
CIDWidths2Expected,
),
vx: self.pdf_text_cid_number(
values[index + 3],
CIDWidths2Expected,
),
vy: self.pdf_text_cid_number(
values[index + 4],
CIDWidths2Expected,
),
}
for code in first_code..<=last_code {
output.push((code, width))
}
index += 5
}
_ => raise CIDWidths2Expected
}
}
_ => raise CIDWidths2Expected
}
}
output
}
///|
fn PdfDocument::pdf_text_cid_widths(
self : PdfDocument,
dictionary : PdfObject,
) -> Array[(Int, Double)] raise PdfError {
match self.lookup_direct(pdf_text_w_key_name, dictionary) {
Some(PdfArray(values)) => self.pdf_text_read_cid_widths(values)
_ => []
}
}
///|
fn PdfDocument::pdf_text_cid_widths2(
self : PdfDocument,
dictionary : PdfObject,
) -> Array[(Int, PdfCIDVerticalWidth)] raise PdfError {
match self.lookup_direct(pdf_text_w2_key_name, dictionary) {
Some(PdfArray(values)) => self.pdf_text_read_cid_widths2(values)
_ => []
}
}
///|
fn PdfDocument::pdf_text_cid_default_width(
self : PdfDocument,
dictionary : PdfObject,
) -> Double raise PdfError {
match self.lookup_direct(pdf_text_dw_key_name, dictionary) {
Some(value) => self.pdf_text_cid_number(value, CIDWidthsExpected)
None => 1000.0
}
}
///|
fn PdfDocument::pdf_text_cid_default_width2(
self : PdfDocument,
dictionary : PdfObject,
) -> Array[Double] raise PdfError {
match self.lookup_direct(pdf_text_dw2_key_name, dictionary) {
Some(PdfArray(values)) => {
let output : Array[Double] = []
for value in values {
output.push(self.pdf_text_cid_number(value, CIDWidths2Expected))
}
output
}
_ => [880.0, -1000.0]
}
}
///|
fn PdfDocument::pdf_text_read_descendant(
self : PdfDocument,
dictionary : PdfObject,
) -> PdfCompositeCIDFont raise PdfError {
let cid_system_info = match
self.lookup_direct(pdf_text_cid_system_info_key_name, dictionary) {
Some(system_info) => self.read_cid_system_info(system_info)
None => raise CIDSystemInfoExpected
}
let cid_basefont = match
self.lookup_direct(pdf_text_base_font_key_name, dictionary) {
Some(PdfNameObject(name)) => name
_ => raise CIDBaseFontExpected
}
let cid_fontdescriptor = match self.read_font_descriptor(dictionary) {
Some(fontdescriptor) => fontdescriptor
None => raise CIDFontDescriptorExpected
}
{
cid_system_info,
cid_basefont,
cid_fontdescriptor,
cid_widths: self.pdf_text_cid_widths(dictionary),
cid_widths2: self.pdf_text_cid_widths2(dictionary),
cid_default_width: self.pdf_text_cid_default_width(dictionary),
cid_default_width2: self.pdf_text_cid_default_width2(dictionary),
}
}
///|
fn PdfDocument::pdf_text_read_cmap_encoding(
self : PdfDocument,
font : PdfObject,
) -> PdfCMapEncoding raise PdfError {
match self.lookup_direct(pdf_text_encoding_key_name, font) {
Some(PdfNameObject(name)) => PdfPredefinedCMap(name)
Some(PdfStreamObject(_)) =>
match pdf_text_find_immediate_indirect(font, pdf_text_encoding_key_name) {
Some(number) =>
try self.parse_cmap(PdfIndirect(number)) catch {
_ => PdfCMap(number)
} noraise {
parsed => PdfExternalCMap(number, parsed)
}
None => raise CMapEncodingExpected
}
_ => raise CMapEncodingExpected
}
}
///|
/// Parse a Type 0 font dictionary into a CID-keyed font.
///
/// This reads the descendant CIDFont, width data, descriptor, base font, and
/// CMap encoding. External CMap streams are parsed when possible while still
/// preserving the referenced stream object number.
pub fn PdfDocument::read_cidkeyed_font(
self : PdfDocument,
font : PdfObject,
) -> PdfCIDKeyedFont raise PdfError {
let basefont = match self.lookup_direct(pdf_text_base_font_key_name, font) {
Some(PdfNameObject(name)) => name
_ => raise BaseFontExpected
}
let composite = match
self.lookup_direct(pdf_text_descendant_fonts_key_name, font) {
Some(PdfArray([descendant])) =>
self.pdf_text_read_descendant(self.direct(descendant))
_ => raise DescendantFontExpected
}
{ basefont, composite, encoding: self.pdf_text_read_cmap_encoding(font) }
}
///|
fn pdf_text_hex_digit_value(byte : Byte) -> Int? {
let value = byte.to_int()
if value >= 48 && value <= 57 {
Some(value - 48)
} else if value >= 65 && value <= 70 {
Some(value - 55)
} else if value >= 97 && value <= 102 {
Some(value - 87)
} else {
None
}
}
///|
fn pdf_text_parse_hex_bytes(
line : BytesView,
start : Int,
stop : Int,
) -> PdfBytes? {
guard stop >= start else { return None }
let mut digit_count = 0
let mut scan = start
while scan < stop {
let value = line[scan].to_int()
if pdf_is_whitespace_byte(value) {
()
} else {
match pdf_text_hex_digit_value(line[scan]) {
Some(_) => digit_count += 1
None => return None
}
}
scan += 1
}
let output = Array::make((digit_count + 1) / 2, b'\x00')
let mut high : Int? = None
let mut position = 0
let mut index = start
while index < stop {
let value = line[index].to_int()
if pdf_is_whitespace_byte(value) {
()
} else {
match pdf_text_hex_digit_value(line[index]) {
Some(nibble) =>
match high {
Some(high_nibble) => {
output[position] = (high_nibble * 16 + nibble).to_byte()
position += 1
high = None
}
None => high = Some(nibble)
}
None => ()
}
}
index += 1
}
if high is Some(high_nibble) {
output[position] = (high_nibble * 16).to_byte()
}
Some(Bytes::from_array(output))
}
///|
fn pdf_text_skip_cmap_whitespace(line : BytesView, start : Int) -> Int {
let mut index = start
while index < line.length() && pdf_is_whitespace_byte(line[index].to_int()) {
index += 1
}
index
}
///|
fn pdf_text_line_contains_ascii(line : BytesView, word : String) -> Bool {
pdf_text_index_of_ascii(line, word) != None
}
///|
fn pdf_text_index_of_ascii(line : BytesView, word : String) -> Int? {
let needle = @ascii.encode(word)
guard needle.length() > 0 && line.length() >= needle.length() else {
return None
}
for index in 0..<=(line.length() - needle.length()) {
let mut matched = true
for offset in 0.. Int? {
guard start < line.length() else { return None }
match pdf_text_index_of_ascii(line[start:], word) {
Some(index) => Some(start + index)
None => None
}
}
///|
fn pdf_text_after_ascii(line : BytesView, word : String) -> BytesView? {
match pdf_text_index_of_ascii(line, word) {
Some(index) => {
let word_length = @ascii.encode(word).length()
Some(line[index + word_length:])
}
None => None
}
}
///|
fn pdf_text_view_equals_ascii(view : BytesView, text : String) -> Bool {
let expected = @ascii.encode(text)
guard view.length() == expected.length() else { return false }
for index in 0.. Int? {
let cursor = byte_cursor_of_view(data)
let mut expect_value = false
for line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(line)
let tokens = pdf_split_whitespace_tokens(uncommented)
for token in tokens {
if expect_value {
expect_value = false
let parsed = try pdf_parse_ascii_int_view(token) catch {
_ => None
} noraise {
value => Some(value)
}
match parsed {
Some(value) => return Some(value)
None => ()
}
}
if pdf_text_view_equals_ascii(token, key) {
expect_value = true
}
}
} nobreak {
None
}
}
///|
fn pdf_text_parse_cmap_wmode(data : BytesView) -> Int? {
pdf_text_parse_cmap_int_after_token(data, "/WMode")
}
///|
fn pdf_text_parse_cmap_name_token(token : BytesView) -> PdfName? {
guard token.length() > 1 && token[0].to_int() == 47 else { return None }
let bytes : Array[Byte] = [47]
let mut index = 1
while index < token.length() {
let value = token[index].to_int()
if value == 35 {
guard index + 2 < token.length() else { return None }
match
(
pdf_hex_value(token[index + 1].to_int()),
pdf_hex_value(token[index + 2].to_int()),
) {
(Some(high), Some(low)) => {
bytes.push((high * 16 + low).to_byte())
index += 3
}
_ => return None
}
} else {
bytes.push(token[index])
index += 1
}
}
Some(pdf_name_of_bytes(Bytes::from_array(bytes)))
}
///|
fn pdf_text_parse_cmap_name_after_token(
data : BytesView,
key : String,
) -> PdfName? {
let cursor = byte_cursor_of_view(data)
let mut expect_value = false
for line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(line)
let tokens = pdf_split_whitespace_tokens(uncommented)
for token in tokens {
if expect_value {
expect_value = false
match pdf_text_parse_cmap_name_token(token) {
Some(name) => return Some(name)
None => ()
}
}
if pdf_text_view_equals_ascii(token, key) {
expect_value = true
}
}
} nobreak {
None
}
}
///|
fn pdf_text_parse_cmap_object_token(token : BytesView) -> PdfObject? {
try pdf_parse_object_from_view(token) catch {
_ => None
} noraise {
object => Some(object)
}
}
///|
priv enum PdfTextCMapCIDSystemInfoKey {
PdfTextCMapCIDSystemRegistry
PdfTextCMapCIDSystemOrdering
PdfTextCMapCIDSystemSupplement
}
///|
fn pdf_text_parse_cmap_cid_system_value(
key : PdfTextCMapCIDSystemInfoKey,
token : BytesView,
registry : Array[PdfBytes],
ordering : Array[PdfBytes],
supplement : Array[Int],
) -> Unit {
match (key, pdf_text_parse_cmap_object_token(token)) {
(PdfTextCMapCIDSystemRegistry, Some(PdfString(value))) =>
registry.push(value)
(PdfTextCMapCIDSystemOrdering, Some(PdfString(value))) =>
ordering.push(value)
(PdfTextCMapCIDSystemSupplement, Some(PdfInteger(value))) =>
supplement.push(value)
_ => ()
}
}
///|
fn pdf_text_parse_cmap_cid_system_info(data : BytesView) -> PdfCIDSystemInfo? {
let cursor = byte_cursor_of_view(data)
let registries : Array[PdfBytes] = []
let orderings : Array[PdfBytes] = []
let supplements : Array[Int] = []
let mut seen_cid_system_info = false
let mut expect_value : PdfTextCMapCIDSystemInfoKey? = None
for line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(line)
let tokens = pdf_split_whitespace_tokens(uncommented)
for token in tokens {
if !seen_cid_system_info {
if pdf_text_view_equals_ascii(token, "/CIDSystemInfo") {
seen_cid_system_info = true
}
continue
}
match expect_value {
Some(key) => {
pdf_text_parse_cmap_cid_system_value(
key, token, registries, orderings, supplements,
)
expect_value = None
if registries.length() > 0 &&
orderings.length() > 0 &&
supplements.length() > 0 {
return Some({
registry: registries[0],
ordering: orderings[0],
supplement: supplements[0],
})
}
}
None => ()
}
if pdf_text_view_equals_ascii(token, "/Registry") {
expect_value = Some(PdfTextCMapCIDSystemRegistry)
} else if pdf_text_view_equals_ascii(token, "/Ordering") {
expect_value = Some(PdfTextCMapCIDSystemOrdering)
} else if pdf_text_view_equals_ascii(token, "/Supplement") {
expect_value = Some(PdfTextCMapCIDSystemSupplement)
}
}
} nobreak {
None
}
}
///|
fn pdf_text_parse_cmap_usecmap(data : BytesView) -> PdfName? {
let cursor = byte_cursor_of_view(data)
let mut previous_name : PdfName? = None
for line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(line)
let tokens = pdf_split_whitespace_tokens(uncommented)
for token in tokens {
if pdf_text_view_equals_ascii(token, "usecmap") {
match previous_name {
Some(name) => return Some(name)
None => ()
}
}
previous_name = pdf_text_parse_cmap_name_token(token)
}
} nobreak {
None
}
}
///|
fn pdf_text_cmap_end_marker(line : BytesView, start : Int) -> (Int, Int)? {
let markers = [
"endbfchar", "endbfrange", "endcidchar", "endcidrange", "endnotdefchar", "endnotdefrange",
"endcodespacerange",
]
let mut best : (Int, Int)? = None
for marker in markers {
match pdf_text_index_of_ascii_from(line, marker, start) {
Some(index) => {
let length = @ascii.encode(marker).length()
match best {
Some((best_index, _)) if best_index <= index => ()
_ => best = Some((index, length))
}
}
None => ()
}
}
best
}
///|
fn pdf_text_cmap_section_line_views(line : BytesView) -> Array[BytesView] {
let views : Array[BytesView] = []
let mut start = 0
while start < line.length() {
match pdf_text_cmap_end_marker(line, start) {
Some((index, length)) => {
let stop = index + length
views.push(line[start:stop])
start = stop
}
None => {
views.push(line[start:])
break
}
}
}
views
}
///|
fn pdf_text_cmap_comment_start(line : BytesView) -> Int {
let mut in_literal = false
let mut escaped = false
let mut literal_depth = 0
for index in 0.. PdfBytes {
let stop = pdf_text_cmap_comment_start(line)
let output = Array::make(stop, b'\x00')
for index in 0.. Array[PdfBytes]? {
let groups : Array[PdfBytes] = []
let mut index = 0
while index < line.length() {
index = pdf_text_skip_cmap_whitespace(line, index)
if index >= line.length() {
break
}
if line[index].to_int() != 60 {
break
}
let start = index + 1
let mut stop = start
while stop < line.length() && line[stop].to_int() != 62 {
stop += 1
}
guard stop < line.length() else { return None }
match pdf_text_parse_hex_bytes(line, start, stop) {
Some(bytes) => groups.push(bytes)
None => return None
}
index = stop + 1
}
if groups.length() == 0 {
None
} else {
Some(groups)
}
}
///|
fn pdf_text_parse_cmap_hex_group_at(
line : BytesView,
start : Int,
) -> (PdfBytes, Int)? {
let index = pdf_text_skip_cmap_whitespace(line, start)
guard index < line.length() && line[index].to_int() == 60 else { return None }
let body_start = index + 1
let mut stop = body_start
while stop < line.length() && line[stop].to_int() != 62 {
stop += 1
}
guard stop < line.length() else { return None }
match pdf_text_parse_hex_bytes(line, body_start, stop) {
Some(bytes) => Some((bytes, stop + 1))
None => None
}
}
///|
fn pdf_text_bytes_to_int(bytes : BytesView) -> Int? {
guard bytes.length() > 0 else { return None }
let mut value = 0
for byte in bytes {
value = (value << 8) | byte.to_int()
}
Some(value)
}
///|
fn pdf_text_parse_cmap_ascii_int_at(
line : BytesView,
start : Int,
) -> (Int, Int)? {
let index = pdf_text_skip_cmap_whitespace(line, start)
guard index < line.length() else { return None }
let mut stop = index
if line[stop].to_int() == 43 || line[stop].to_int() == 45 {
stop += 1
}
let digit_start = stop
while stop < line.length() {
let value = line[stop].to_int()
if value >= 48 && value <= 57 {
stop += 1
} else {
break
}
}
guard stop > digit_start else { return None }
try pdf_parse_ascii_int_view(line[index:stop]) catch {
_ => None
} noraise {
value => Some((value, stop))
}
}
///|
fn pdf_text_index_of_byte(line : BytesView, target : Int, start : Int) -> Int? {
let mut index = start
while index < line.length() {
if line[index].to_int() == target {
break Some(index)
}
index += 1
} nobreak {
None
}
}
///|
fn pdf_text_tounicode_bfrange_inline_entries(
line : BytesView,
) -> Array[(Int, PdfBytes)]? {
let entries : Array[(Int, PdfBytes)] = []
let mut index = 0
while index < line.length() {
match pdf_text_parse_cmap_hex_group_at(line, index) {
Some((source, after_source)) =>
match pdf_text_parse_cmap_hex_group_at(line, after_source) {
Some((stop, after_stop)) =>
match (pdf_text_bytes_to_int(source), pdf_text_bytes_to_int(stop)) {
(Some(first), Some(last)) if first <= last => {
index = pdf_text_skip_cmap_whitespace(line, after_stop)
if index < line.length() && line[index].to_int() == 91 {
match pdf_text_index_of_byte(line, 93, index + 1) {
Some(close) => {
match
pdf_text_parse_cmap_hex_groups(line[index + 1:close]) {
Some(unicodes) =>
match
pdf_text_tounicode_bfrange_array_entries(
first, last, unicodes,
) {
Some(line_entries) =>
for entry in line_entries {
entries.push(entry)
}
None => return None
}
None => return None
}
index = close + 1
}
None => return None
}
} else {
match pdf_text_parse_cmap_hex_group_at(line, index) {
Some((unicode, after_unicode)) => {
for code in first..<=last {
match
pdf_text_add_to_big_endian_bytes(
unicode,
code - first,
) {
Some(bytes) => entries.push((code, bytes))
None => return None
}
}
index = after_unicode
}
None => return None
}
}
}
_ => return None
}
None => return None
}
None => break
}
}
if entries.length() == 0 {
None
} else {
Some(entries)
}
}
///|
fn pdf_text_add_to_big_endian_bytes(
bytes : PdfBytes,
increment : Int,
) -> PdfBytes? {
guard increment >= 0 else { return None }
let output = bytes.to_array()
let mut carry = increment
let mut index = output.length()
while index > 0 && carry > 0 {
index -= 1
let sum = output[index].to_int() + carry % 256
output[index] = (sum % 256).to_byte()
carry = carry / 256 + sum / 256
}
if carry == 0 {
Some(Bytes::from_array(output))
} else {
None
}
}
///|
fn pdf_text_tounicode_bfrange_array_entries(
first : Int,
last : Int,
unicodes : ArrayView[PdfBytes],
) -> Array[(Int, PdfBytes)]? {
guard first <= last && unicodes.length() == last - first + 1 else {
return None
}
let entries : Array[(Int, PdfBytes)] = []
for index in 0.. Unit {
match pdf_text_bytes_to_int(source) {
Some(code) => entries.push((code, unicode))
None => ()
}
}
///|
fn pdf_text_append_tounicode_bfchar_entries(
entries : Array[(Int, PdfBytes)],
pending_source : PdfBytes?,
line : BytesView,
) -> PdfBytes? {
let mut pending = pending_source
match pdf_text_parse_cmap_hex_groups(line) {
Some(groups) => {
let mut index = 0
match pending {
Some(source) =>
if groups.length() > 0 {
pdf_text_push_tounicode_bfchar_entry(entries, source, groups[0])
pending = None
index = 1
}
None => ()
}
while index + 1 < groups.length() {
pdf_text_push_tounicode_bfchar_entry(
entries,
groups[index],
groups[index + 1],
)
index += 2
}
if index < groups.length() {
pending = Some(groups[index])
}
pending
}
None => pending
}
}
///|
fn pdf_text_tounicode_bfrange_entries_of_line(
line : BytesView,
) -> Array[(Int, PdfBytes)]? {
pdf_text_tounicode_bfrange_inline_entries(line)
}
///|
fn pdf_text_push_tounicode_bfrange_entries(
entries : Array[(Int, PdfBytes)],
line_entries : ArrayView[(Int, PdfBytes)],
) -> Unit {
for entry in line_entries {
entries.push(entry)
}
}
///|
priv struct PdfTextCMapBFRangeArray {
first : Int
last : Int
unicodes : Array[PdfBytes]
}
///|
fn pdf_text_extend_cmap_hex_groups(
output : Array[PdfBytes],
line : BytesView,
) -> Unit {
match pdf_text_parse_cmap_hex_groups(line) {
Some(groups) =>
for group in groups {
output.push(group)
}
None => ()
}
}
///|
fn pdf_text_cmap_bfrange_array_line(line : BytesView) -> BytesView {
match pdf_text_index_of_byte(line, 91, 0) {
Some(open) => line[open + 1:]
None => line
}
}
///|
priv enum PdfTextCMapBFRangeArrayAppend {
PdfTextCMapBFRangeArrayPending(PdfTextCMapBFRangeArray)
PdfTextCMapBFRangeArrayClosed(BytesView)
}
///|
fn pdf_text_append_pending_bfrange_array(
entries : Array[(Int, PdfBytes)],
pending : PdfTextCMapBFRangeArray,
line : BytesView,
) -> PdfTextCMapBFRangeArrayAppend {
let content = pdf_text_cmap_bfrange_array_line(line)
match pdf_text_index_of_byte(content, 93, 0) {
Some(close) => {
pdf_text_extend_cmap_hex_groups(pending.unicodes, content[0:close])
match
pdf_text_tounicode_bfrange_array_entries(
pending.first,
pending.last,
pending.unicodes,
) {
Some(line_entries) =>
pdf_text_push_tounicode_bfrange_entries(entries, line_entries)
None => ()
}
PdfTextCMapBFRangeArrayClosed(content[close + 1:])
}
None => {
pdf_text_extend_cmap_hex_groups(pending.unicodes, content)
PdfTextCMapBFRangeArrayPending(pending)
}
}
}
///|
priv enum PdfTextCMapBFRangeLineAppend {
PdfTextCMapBFRangeLineDone
PdfTextCMapBFRangeLinePending(PdfTextCMapBFRangeArray)
PdfTextCMapBFRangeLineContinue(BytesView)
}
///|
fn pdf_text_append_tounicode_bfrange_entry(
entries : Array[(Int, PdfBytes)],
line : BytesView,
) -> PdfTextCMapBFRangeLineAppend {
match pdf_text_parse_cmap_hex_group_at(line, 0) {
Some((source, after_source)) =>
match pdf_text_parse_cmap_hex_group_at(line, after_source) {
Some((stop, after_stop)) =>
match (pdf_text_bytes_to_int(source), pdf_text_bytes_to_int(stop)) {
(Some(first), Some(last)) if first <= last => {
let value_start = pdf_text_skip_cmap_whitespace(line, after_stop)
let pending : PdfTextCMapBFRangeArray = {
first,
last,
unicodes: [],
}
if value_start >= line.length() {
PdfTextCMapBFRangeLinePending(pending)
} else if line[value_start].to_int() == 91 {
match
pdf_text_append_pending_bfrange_array(
entries,
pending,
line[value_start + 1:],
) {
PdfTextCMapBFRangeArrayClosed(rest) =>
PdfTextCMapBFRangeLineContinue(rest)
PdfTextCMapBFRangeArrayPending(pending) =>
PdfTextCMapBFRangeLinePending(pending)
}
} else {
match pdf_text_parse_cmap_hex_group_at(line, value_start) {
Some((unicode, after_unicode)) => {
let line_entries : Array[(Int, PdfBytes)] = []
for code in first..<=last {
match
pdf_text_add_to_big_endian_bytes(unicode, code - first) {
Some(bytes) => line_entries.push((code, bytes))
None => return PdfTextCMapBFRangeLineDone
}
}
pdf_text_push_tounicode_bfrange_entries(
entries, line_entries,
)
PdfTextCMapBFRangeLineContinue(line[after_unicode:])
}
None => PdfTextCMapBFRangeLineDone
}
}
}
_ => PdfTextCMapBFRangeLineDone
}
None => PdfTextCMapBFRangeLineDone
}
None => PdfTextCMapBFRangeLineDone
}
}
///|
fn pdf_text_append_tounicode_bfrange_line(
entries : Array[(Int, PdfBytes)],
line : BytesView,
) -> PdfTextCMapBFRangeArray? {
match pdf_text_tounicode_bfrange_entries_of_line(line) {
Some(line_entries) => {
pdf_text_push_tounicode_bfrange_entries(entries, line_entries)
return None
}
None => ()
}
let mut current = line
while current.length() > 0 {
match pdf_text_append_tounicode_bfrange_entry(entries, current) {
PdfTextCMapBFRangeLineDone => return None
PdfTextCMapBFRangeLinePending(pending) => return Some(pending)
PdfTextCMapBFRangeLineContinue(rest) => current = rest
}
}
None
}
///|
priv enum PdfTextToUnicodeSection {
PdfTextToUnicodeNone
PdfTextToUnicodeBFChar
PdfTextToUnicodeBFRange
}
///|
priv enum PdfTextCMapSection {
PdfTextCMapNone
PdfTextCMapCIDChar
PdfTextCMapCIDRange
PdfTextCMapNotDefChar
PdfTextCMapNotDefRange
PdfTextCMapCodeSpace
}
///|
fn pdf_text_cmap_contains_whitespace(data : BytesView) -> Bool {
for byte in data {
if pdf_is_whitespace_byte(byte.to_int()) {
break true
}
} nobreak {
false
}
}
///|
fn pdf_text_cmap_without_whitespace(data : BytesView) -> PdfBytes {
let mut length = 0
for byte in data {
if !pdf_is_whitespace_byte(byte.to_int()) {
length += 1
}
}
let output = Array::make(length, b'\x00')
let mut position = 0
for byte in data {
if !pdf_is_whitespace_byte(byte.to_int()) {
output[position] = byte
position += 1
}
}
Bytes::from_array(output)
}
///|
fn pdf_text_parse_tounicode_sections(
data : BytesView,
) -> Array[(Int, PdfBytes)]? {
let cursor = byte_cursor_of_view(data)
let entries : Array[(Int, PdfBytes)] = []
let mut section = PdfTextToUnicodeNone
let mut pending_bfchar_source : PdfBytes? = None
let mut pending_bfrange_array : PdfTextCMapBFRangeArray? = None
for raw_line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(raw_line)
for raw_segment in pdf_text_cmap_section_line_views(uncommented) {
let mut line = raw_segment
match pdf_text_after_ascii(raw_segment, "beginbfchar") {
Some(rest) => {
section = PdfTextToUnicodeBFChar
line = rest
}
None =>
match pdf_text_after_ascii(raw_segment, "beginbfrange") {
Some(rest) => {
section = PdfTextToUnicodeBFRange
line = rest
}
None => ()
}
}
let end_bfchar = pdf_text_line_contains_ascii(line, "endbfchar")
let end_bfrange = pdf_text_line_contains_ascii(line, "endbfrange")
match pending_bfrange_array {
Some(pending) =>
match pdf_text_append_pending_bfrange_array(entries, pending, line) {
PdfTextCMapBFRangeArrayClosed(rest) =>
pending_bfrange_array = pdf_text_append_tounicode_bfrange_line(
entries, rest,
)
PdfTextCMapBFRangeArrayPending(pending) =>
pending_bfrange_array = Some(pending)
}
None =>
match section {
PdfTextToUnicodeBFChar =>
pending_bfchar_source = pdf_text_append_tounicode_bfchar_entries(
entries, pending_bfchar_source, line,
)
PdfTextToUnicodeBFRange =>
pending_bfrange_array = pdf_text_append_tounicode_bfrange_line(
entries, line,
)
PdfTextToUnicodeNone => ()
}
}
if end_bfchar && section is PdfTextToUnicodeBFChar {
section = PdfTextToUnicodeNone
pending_bfchar_source = None
}
if end_bfrange && section is PdfTextToUnicodeBFRange {
section = PdfTextToUnicodeNone
}
}
}
if entries.length() == 0 {
None
} else {
Some(entries)
}
}
///|
fn pdf_text_push_cmap_cidchar_entries(
entries : Array[(Int, Int)],
line : BytesView,
) -> Unit {
let mut index = 0
while index < line.length() {
match pdf_text_parse_cmap_hex_group_at(line, index) {
Some((source, after_source)) =>
match pdf_text_parse_cmap_ascii_int_at(line, after_source) {
Some((cid, after_cid)) => {
match pdf_text_bytes_to_int(source) {
Some(code) => entries.push((code, cid))
None => ()
}
index = after_cid
}
None => break
}
None => break
}
}
}
///|
fn pdf_text_push_cmap_cidrange_entries(
entries : Array[(Int, Int)],
line : BytesView,
) -> Unit {
let mut index = 0
while index < line.length() {
match pdf_text_parse_cmap_hex_group_at(line, index) {
Some((source, after_source)) =>
match pdf_text_parse_cmap_hex_group_at(line, after_source) {
Some((stop, after_stop)) =>
match pdf_text_parse_cmap_ascii_int_at(line, after_stop) {
Some((cid, after_cid)) => {
match
(pdf_text_bytes_to_int(source), pdf_text_bytes_to_int(stop)) {
(Some(first), Some(last)) if first <= last =>
for code in first..<=last {
entries.push((code, cid + code - first))
}
_ => ()
}
index = after_cid
}
None => break
}
None => break
}
None => break
}
}
}
///|
fn pdf_text_push_cmap_codespace_entries(
entries : Array[PdfCMapCodeSpace],
line : BytesView,
) -> Unit {
let mut index = 0
while index < line.length() {
match pdf_text_parse_cmap_hex_group_at(line, index) {
Some((source, after_source)) =>
match pdf_text_parse_cmap_hex_group_at(line, after_source) {
Some((stop, after_stop)) => {
match (pdf_text_bytes_to_int(source), pdf_text_bytes_to_int(stop)) {
(Some(first), Some(last)) if first <= last &&
source.length() == stop.length() =>
entries.push({ length: source.length(), first, last })
_ => ()
}
index = after_stop
}
None => break
}
None => break
}
}
}
///|
fn pdf_text_parse_cmap_cid_sections(data : BytesView) -> Array[(Int, Int)]? {
let cursor = byte_cursor_of_view(data)
let entries : Array[(Int, Int)] = []
let mut section = PdfTextCMapNone
for raw_line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(raw_line)
for raw_segment in pdf_text_cmap_section_line_views(uncommented) {
let mut line = raw_segment
match pdf_text_after_ascii(raw_segment, "begincidchar") {
Some(rest) => {
section = PdfTextCMapCIDChar
line = rest
}
None =>
match pdf_text_after_ascii(raw_segment, "begincidrange") {
Some(rest) => {
section = PdfTextCMapCIDRange
line = rest
}
None => ()
}
}
match section {
PdfTextCMapCIDChar => pdf_text_push_cmap_cidchar_entries(entries, line)
PdfTextCMapCIDRange =>
pdf_text_push_cmap_cidrange_entries(entries, line)
_ => ()
}
if pdf_text_line_contains_ascii(line, "endcidchar") &&
section is PdfTextCMapCIDChar {
section = PdfTextCMapNone
}
if pdf_text_line_contains_ascii(line, "endcidrange") &&
section is PdfTextCMapCIDRange {
section = PdfTextCMapNone
}
}
}
if entries.length() == 0 {
None
} else {
Some(entries)
}
}
///|
fn pdf_text_parse_cmap_notdef_sections(data : BytesView) -> Array[(Int, Int)]? {
let cursor = byte_cursor_of_view(data)
let entries : Array[(Int, Int)] = []
let mut section = PdfTextCMapNone
for raw_line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(raw_line)
for raw_segment in pdf_text_cmap_section_line_views(uncommented) {
let mut line = raw_segment
match pdf_text_after_ascii(raw_segment, "beginnotdefchar") {
Some(rest) => {
section = PdfTextCMapNotDefChar
line = rest
}
None =>
match pdf_text_after_ascii(raw_segment, "beginnotdefrange") {
Some(rest) => {
section = PdfTextCMapNotDefRange
line = rest
}
None => ()
}
}
match section {
PdfTextCMapNotDefChar =>
pdf_text_push_cmap_cidchar_entries(entries, line)
PdfTextCMapNotDefRange =>
pdf_text_push_cmap_cidrange_entries(entries, line)
_ => ()
}
if pdf_text_line_contains_ascii(line, "endnotdefchar") &&
section is PdfTextCMapNotDefChar {
section = PdfTextCMapNone
}
if pdf_text_line_contains_ascii(line, "endnotdefrange") &&
section is PdfTextCMapNotDefRange {
section = PdfTextCMapNone
}
}
}
if entries.length() == 0 {
None
} else {
Some(entries)
}
}
///|
fn pdf_text_parse_cmap_codespace_sections(
data : BytesView,
) -> Array[PdfCMapCodeSpace]? {
let cursor = byte_cursor_of_view(data)
let entries : Array[PdfCMapCodeSpace] = []
let mut section = PdfTextCMapNone
for raw_line in cursor.read_line_views() {
let uncommented = pdf_text_cmap_line_without_comment(raw_line)
for raw_segment in pdf_text_cmap_section_line_views(uncommented) {
let mut line = raw_segment
match pdf_text_after_ascii(raw_segment, "begincodespacerange") {
Some(rest) => {
section = PdfTextCMapCodeSpace
line = rest
}
None => ()
}
match section {
PdfTextCMapCodeSpace =>
pdf_text_push_cmap_codespace_entries(entries, line)
_ => ()
}
if pdf_text_line_contains_ascii(line, "endcodespacerange") &&
section is PdfTextCMapCodeSpace {
section = PdfTextCMapNone
}
}
}
if entries.length() == 0 {
None
} else {
Some(entries)
}
}
///|
let pdf_text_cmap_split_begin_marker : PdfBytes = b"begin"
///|
let pdf_text_cmap_split_end_marker : PdfBytes = b"end"
///|
let pdf_text_cmap_split_suffixes : ReadOnlyArray[PdfBytes] = [
b"bfchar", b"bfrange", b"cidchar", b"cidrange", b"notdefchar", b"notdefrange",
b"codespacerange",
]
///|
fn pdf_text_cmap_starts_with_at(
data : BytesView,
start : Int,
expected : BytesView,
) -> Bool {
if start < 0 || start + expected.length() > data.length() {
false
} else {
for offset in 0.. Bool {
guard pdf_text_cmap_starts_with_at(data, start, prefix) else { return false }
let whitespace_start = start + prefix.length()
let mut suffix_start = whitespace_start
while suffix_start < data.length() &&
pdf_is_whitespace_byte(data[suffix_start].to_int()) {
suffix_start += 1
}
guard suffix_start > whitespace_start else { return false }
for suffix in pdf_text_cmap_split_suffixes {
if pdf_text_cmap_starts_with_at(data, suffix_start, suffix) {
return true
}
}
false
}
///|
fn pdf_text_cmap_has_split_marker(data : BytesView) -> Bool {
for index in 0.. Array[(Int, Int)]? {
if pdf_text_cmap_contains_whitespace(data) {
let parsed = pdf_text_parse_cmap_cid_sections(data)
if pdf_text_cmap_has_split_marker(data) {
let compact = pdf_text_cmap_without_whitespace(data)
let compact_parsed = pdf_text_parse_cmap_cid_sections(compact)
match (parsed, compact_parsed) {
(Some(original_entries), Some(compact_entries)) =>
if compact_entries.length() > original_entries.length() {
Some(compact_entries)
} else {
Some(original_entries)
}
(None, Some(compact_entries)) => Some(compact_entries)
_ => parsed
}
} else {
parsed
}
} else {
pdf_text_parse_cmap_cid_sections(data)
}
}
///|
fn pdf_text_parse_cmap_notdefs(data : BytesView) -> Array[(Int, Int)]? {
if pdf_text_cmap_contains_whitespace(data) {
let parsed = pdf_text_parse_cmap_notdef_sections(data)
if pdf_text_cmap_has_split_marker(data) {
let compact = pdf_text_cmap_without_whitespace(data)
let compact_parsed = pdf_text_parse_cmap_notdef_sections(compact)
match (parsed, compact_parsed) {
(Some(original_entries), Some(compact_entries)) =>
if compact_entries.length() > original_entries.length() {
Some(compact_entries)
} else {
Some(original_entries)
}
(None, Some(compact_entries)) => Some(compact_entries)
_ => parsed
}
} else {
parsed
}
} else {
pdf_text_parse_cmap_notdef_sections(data)
}
}
///|
fn pdf_text_parse_cmap_codespaces(data : BytesView) -> Array[PdfCMapCodeSpace]? {
if pdf_text_cmap_contains_whitespace(data) {
let parsed = pdf_text_parse_cmap_codespace_sections(data)
if pdf_text_cmap_has_split_marker(data) {
let compact = pdf_text_cmap_without_whitespace(data)
let compact_parsed = pdf_text_parse_cmap_codespace_sections(compact)
match (parsed, compact_parsed) {
(Some(original_entries), Some(compact_entries)) =>
if compact_entries.length() > original_entries.length() {
Some(compact_entries)
} else {
Some(original_entries)
}
(None, Some(compact_entries)) => Some(compact_entries)
_ => parsed
}
} else {
parsed
}
} else {
pdf_text_parse_cmap_codespace_sections(data)
}
}
///|
fn pdf_text_parse_tounicode(data : BytesView) -> Array[(Int, PdfBytes)]? {
if pdf_text_cmap_contains_whitespace(data) {
let parsed = pdf_text_parse_tounicode_sections(data)
if pdf_text_cmap_has_split_marker(data) {
let compact = pdf_text_cmap_without_whitespace(data)
let compact_parsed = pdf_text_parse_tounicode_sections(compact)
match (parsed, compact_parsed) {
(Some(original_entries), Some(compact_entries)) =>
if compact_entries.length() > original_entries.length() {
Some(compact_entries)
} else {
Some(original_entries)
}
(None, Some(compact_entries)) => Some(compact_entries)
_ => parsed
}
} else {
parsed
}
} else {
pdf_text_parse_tounicode_sections(data)
}
}
///|
/// Parse raw CMap or ToUnicode bytes into mapping tables and metadata.
///
/// The parser accepts common CMap sections such as code-space ranges,
/// `bfchar`/`bfrange`, CID ranges, notdef ranges, `/UseCMap`, `/WMode`, and
/// CID-system metadata. Unrecognized or malformed sections are skipped rather
/// than causing a document-level failure.
pub fn pdf_parse_cmap_data(data : BytesView) -> PdfParsedCMap {
{
map: match pdf_text_parse_tounicode(data) {
Some(entries) => entries
None => []
},
cid_map: match pdf_text_parse_cmap_cids(data) {
Some(entries) => entries
None => []
},
notdef_map: match pdf_text_parse_cmap_notdefs(data) {
Some(entries) => entries
None => []
},
codespaces: match pdf_text_parse_cmap_codespaces(data) {
Some(entries) => entries
None => []
},
usecmap: pdf_text_parse_cmap_usecmap(data),
wmode: pdf_text_parse_cmap_wmode(data),
cmap_name: pdf_text_parse_cmap_name_after_token(data, "/CMapName"),
cmap_type: pdf_text_parse_cmap_int_after_token(data, "/CMapType"),
cid_system_info: pdf_text_parse_cmap_cid_system_info(data),
}
}
///|
fn pdf_text_tounicode_has_charcode(
entries : ArrayView[(Int, PdfBytes)],
code : Int,
) -> Bool {
for entry in entries {
if entry.0 == code {
break true
}
} nobreak {
false
}
}
///|
fn pdf_text_compose_tounicode_entries(
current : ArrayView[(Int, PdfBytes)],
inherited : ArrayView[(Int, PdfBytes)],
) -> Array[(Int, PdfBytes)] {
let output : Array[(Int, PdfBytes)] = []
let seen : @hashmap.HashMap[Int, Bool] = HashMap([])
for entry in current {
output.push(entry)
seen[entry.0] = true
}
for entry in inherited {
if !seen.contains(entry.0) {
seen[entry.0] = true
output.push(entry)
}
}
output
}
///|
fn pdf_text_compose_cid_entries(
current : ArrayView[(Int, Int)],
inherited : ArrayView[(Int, Int)],
) -> Array[(Int, Int)] {
let output : Array[(Int, Int)] = []
let seen : @hashmap.HashMap[Int, Bool] = HashMap([])
for entry in current {
output.push(entry)
seen[entry.0] = true
}
for entry in inherited {
if !seen.contains(entry.0) {
seen[entry.0] = true
output.push(entry)
}
}
output
}
///|
fn pdf_text_compose_codespaces(
current : ArrayView[PdfCMapCodeSpace],
inherited : ArrayView[PdfCMapCodeSpace],
) -> Array[PdfCMapCodeSpace] {
let output : Array[PdfCMapCodeSpace] = []
for entry in current {
output.push(entry)
}
for entry in inherited {
output.push(entry)
}
output
}
///|
fn pdf_text_compose_parsed_cmap(
current : PdfParsedCMap,
inherited : PdfParsedCMap,
) -> PdfParsedCMap {
{
map: pdf_text_compose_tounicode_entries(current.map, inherited.map),
cid_map: pdf_text_compose_cid_entries(current.cid_map, inherited.cid_map),
notdef_map: pdf_text_compose_cid_entries(
current.notdef_map,
inherited.notdef_map,
),
codespaces: pdf_text_compose_codespaces(
current.codespaces,
inherited.codespaces,
),
usecmap: match current.usecmap {
Some(_) => current.usecmap
None => inherited.usecmap
},
wmode: match current.wmode {
Some(_) => current.wmode
None => inherited.wmode
},
cmap_name: match current.cmap_name {
Some(_) => current.cmap_name
None => inherited.cmap_name
},
cmap_type: match current.cmap_type {
Some(_) => current.cmap_type
None => inherited.cmap_type
},
cid_system_info: match current.cid_system_info {
Some(_) => current.cid_system_info
None => inherited.cid_system_info
},
}
}
///|
fn PdfDocument::pdf_text_cmap_stream_dictionary_wmode(
self : PdfDocument,
stream_object : PdfObject,
) -> Int? {
match self.lookup_direct(pdf_text_wmode_key_name, stream_object) {
Some(PdfInteger(value)) => Some(value)
_ => None
}
}
///|
fn PdfDocument::pdf_text_cmap_stream_dictionary_cmap_name(
self : PdfDocument,
stream_object : PdfObject,
) -> PdfName? {
match self.lookup_direct(pdf_text_cmap_name_key_name, stream_object) {
Some(PdfNameObject(name)) => Some(name)
_ => None
}
}
///|
fn PdfDocument::pdf_text_cmap_stream_dictionary_cmap_type(
self : PdfDocument,
stream_object : PdfObject,
) -> Int? {
match self.lookup_direct(pdf_text_cmap_type_key_name, stream_object) {
Some(PdfInteger(value)) => Some(value)
_ => None
}
}
///|
fn PdfDocument::pdf_text_cmap_stream_dictionary_usecmap_name(
self : PdfDocument,
stream_object : PdfObject,
) -> PdfName? {
match self.lookup_direct(pdf_text_usecmap_key_name, stream_object) {
Some(PdfNameObject(name)) => Some(name)
_ => None
}
}
///|
fn PdfDocument::pdf_text_cmap_stream_dictionary_cid_system_info(
self : PdfDocument,
stream_object : PdfObject,
) -> PdfCIDSystemInfo? {
match self.lookup_direct(pdf_text_cid_system_info_key_name, stream_object) {
Some(value) =>
try self.read_cid_system_info(value) catch {
_ => None
} noraise {
info => Some(info)
}
None => None
}
}
///|
fn PdfDocument::pdf_text_apply_cmap_stream_dictionary_metadata(
self : PdfDocument,
stream_object : PdfObject,
parsed : PdfParsedCMap,
) -> PdfParsedCMap {
{
..parsed,
usecmap: match parsed.usecmap {
Some(_) => parsed.usecmap
None => self.pdf_text_cmap_stream_dictionary_usecmap_name(stream_object)
},
wmode: match parsed.wmode {
Some(_) => parsed.wmode
None => self.pdf_text_cmap_stream_dictionary_wmode(stream_object)
},
cmap_name: match parsed.cmap_name {
Some(_) => parsed.cmap_name
None => self.pdf_text_cmap_stream_dictionary_cmap_name(stream_object)
},
cmap_type: match parsed.cmap_type {
Some(_) => parsed.cmap_type
None => self.pdf_text_cmap_stream_dictionary_cmap_type(stream_object)
},
cid_system_info: match parsed.cid_system_info {
Some(_) => parsed.cid_system_info
None =>
self.pdf_text_cmap_stream_dictionary_cid_system_info(stream_object)
},
}
}
///|
fn PdfDocument::pdf_text_decoded_cmap_stream_data_direct(
self : PdfDocument,
object : PdfObject,
) -> PdfBytes raise PdfError {
match self.direct(object) {
PdfStreamObject(stream) => {
let decoded = match
self.pdf_stream_first_filter_direct(stream.dictionary) {
None => stream
Some(_) => self.pdf_decode_stream_value_direct(stream)
}
pdf_stream_data_bytes(decoded.data)
}
_ => raise CMapEncodingExpected
}
}
///|
fn PdfDocument::parse_cmap_with_seen(
self : PdfDocument,
cmap : PdfObject,
seen : @hashmap.HashMap[Int, Bool],
) -> PdfParsedCMap raise PdfError {
match cmap {
PdfIndirect(number) => {
guard !seen.contains(number) else { raise CMapEncodingExpected }
seen[number] = true
}
_ => ()
}
let bytes = self.pdf_text_decoded_cmap_stream_data_direct(cmap)
let stream_object = self.direct(cmap)
let parsed = self.pdf_text_apply_cmap_stream_dictionary_metadata(
stream_object,
pdf_parse_cmap_data(bytes),
)
match
(parsed.usecmap, stream_object.lookup_immediate(pdf_text_usecmap_key_name)) {
(None, Some(base)) =>
match base {
PdfIndirect(_) | PdfStreamObject(_) =>
try self.parse_cmap_with_seen(base, seen) catch {
_ => parsed
} noraise {
inherited => pdf_text_compose_parsed_cmap(parsed, inherited)
}
_ => parsed
}
_ => parsed
}
}
///|
/// Decode and parse a CMap stream object in this document.
///
/// The stream is decoded through its first filter, stream-dictionary metadata
/// is merged with parsed metadata, and indirect `/UseCMap` bases are composed
/// with cycle protection. Malformed or non-stream inputs raise `PdfError`.
pub fn PdfDocument::parse_cmap(
self : PdfDocument,
cmap : PdfObject,
) -> PdfParsedCMap raise PdfError {
self.parse_cmap_with_seen(cmap, HashMap([]))
}
///|
/// Compatibility wrapper for `PdfDocument::parse_cmap`.
pub fn pdf_parse_cmap(
document : PdfDocument,
cmap : PdfObject,
) -> PdfParsedCMap raise PdfError {
document.parse_cmap(cmap)
}
///|
fn PdfDocument::pdf_text_tounicode_of_font(
self : PdfDocument,
font : PdfObject,
) -> Array[(Int, PdfBytes)]? {
match self.lookup_direct(pdf_text_tounicode_key_name, font) {
Some(PdfStreamObject(_) as stream) =>
try self.parse_cmap(stream) catch {
_ => None
} noraise {
parsed => if parsed.map.length() == 0 { None } else { Some(parsed.map) }
}
_ => None
}
}
///|
fn PdfFontDescriptor::pdf_text_with_tounicode(
self : PdfFontDescriptor,
tounicode : Array[(Int, PdfBytes)],
) -> PdfFontDescriptor {
{ ..self, tounicode: Some(tounicode) }
}
///|
fn PdfFont::pdf_text_with_tounicode(
self : PdfFont,
tounicode : Array[(Int, PdfBytes)]?,
) -> PdfFont {
match tounicode {
None => self
Some(tounicode) =>
match self {
PdfFontSimple(simple) => {
let descriptor = match simple.fontdescriptor {
Some(descriptor) => descriptor
None => pdf_text_empty_font_descriptor()
}
PdfFontSimple({
..simple,
fontdescriptor: Some(descriptor.pdf_text_with_tounicode(tounicode)),
})
}
PdfFontCIDKeyed(cid_font) => {
let composite = {
..cid_font.composite,
cid_fontdescriptor: cid_font.composite.cid_fontdescriptor.pdf_text_with_tounicode(
tounicode,
),
}
PdfFontCIDKeyed({ ..cid_font, composite, })
}
PdfFontStandard(_) => self
}
}
}
///|
/// Read a standard 14 font dictionary.
///
/// The dictionary must contain a recognized `/BaseFont`; its encoding is read
/// with `read_encoding` so custom differences are preserved.
pub fn PdfDocument::read_standard14_font(
self : PdfDocument,
font : PdfObject,
) -> PdfStandardFontData raise PdfError {
match self.lookup_direct(pdf_text_base_font_key_name, font) {
Some(PdfNameObject(base_font)) =>
match pdf_standard_font_of_pdf_name(base_font) {
Some(standard_font) =>
{ font: standard_font, encoding: self.read_encoding(font) }
None => raise StandardFontExpected
}
_ => raise BaseFontExpected
}
}
///|
/// Read any supported PDF font dictionary.
///
/// The result is classified as standard 14, simple, or CID-keyed. A
/// `/ToUnicode` stream, when present and parseable, is attached to the parsed
/// font so extractors prefer explicit Unicode mappings.
pub fn PdfDocument::read_font(
self : PdfDocument,
font : PdfObject,
) -> PdfFont raise PdfError {
let read = if self.is_standard14_font(font) {
PdfFontStandard(self.read_standard14_font(font))
} else if self.is_simple_font(font) {
PdfFontSimple(self.read_simple_font(font))
} else if self.is_cidkeyed_font(font) {
PdfFontCIDKeyed(self.read_cidkeyed_font(font))
} else {
raise FontTypeExpected
}
read.pdf_text_with_tounicode(self.pdf_text_tounicode_of_font(font))
}
///|
/// Compatibility wrapper for `PdfDocument::read_font`.
pub fn pdf_read_font(
document : PdfDocument,
font : PdfObject,
) -> PdfFont raise PdfError {
document.read_font(font)
}
///|
/// Read a font dictionary and return a text extractor for it.
pub fn PdfDocument::text_extractor_of_font(
self : PdfDocument,
font : PdfObject,
) -> PdfTextExtractor raise PdfError {
self.read_font(font).text_extractor()
}
///|
/// Compatibility wrapper for `PdfDocument::text_extractor_of_font`.
pub fn pdf_text_extractor_of_font(
document : PdfDocument,
font : PdfObject,
) -> PdfTextExtractor raise PdfError {
document.text_extractor_of_font(font)
}
///|
fn PdfFont::pdf_text_tounicode(self : PdfFont) -> Array[(Int, PdfBytes)]? {
match self {
PdfFontSimple(
{ fontdescriptor: Some({ tounicode: Some(tounicode), .. }), .. }
) => Some(tounicode)
PdfFontCIDKeyed(
{
composite: {
cid_fontdescriptor: { tounicode: Some(tounicode), .. },
..,
},
..,
}
) => Some(tounicode)
_ => None
}
}
///|
fn pdf_text_lookup_tounicode(
tounicode : ArrayView[(Int, PdfBytes)],
code : Int,
) -> PdfBytes? {
for entry in tounicode {
if entry.0 == code {
break Some(entry.1)
}
} nobreak {
None
}
}
///|
fn pdf_text_codepoints_of_tounicode_bytes_or_charcode(
bytes : PdfBytes,
code : Int,
) -> Array[Int] {
try pdf_codepoints_of_utf16be(bytes) catch {
_ => [code]
} noraise {
codepoints => codepoints
}
}
///|
fn pdf_text_lookup_tounicode_codepoints(
tounicode : ArrayView[(Int, PdfBytes)],
code : Int,
) -> Array[Int]? {
match pdf_text_lookup_tounicode(tounicode, code) {
Some(bytes) =>
Some(pdf_text_codepoints_of_tounicode_bytes_or_charcode(bytes, code))
None => None
}
}
///|
priv struct PdfTextExternalCMapLookup {
cid_map : @hashmap.HashMap[Int, Int]
notdef_map : @hashmap.HashMap[Int, Int]
map : @hashmap.HashMap[Int, Array[Int]]
}
///|
fn pdf_text_cmap_cid_lookup_map(
entries : ArrayView[(Int, Int)],
) -> @hashmap.HashMap[Int, Int] {
let values : @hashmap.HashMap[Int, Int] = HashMap([])
for entry in entries {
if !values.contains(entry.0) {
values[entry.0] = entry.1
}
}
values
}
///|
fn pdf_text_tounicode_codepoints_lookup_map(
entries : ArrayView[(Int, PdfBytes)],
) -> @hashmap.HashMap[Int, Array[Int]] {
let values : @hashmap.HashMap[Int, Array[Int]] = HashMap([])
for entry in entries {
if !values.contains(entry.0) {
values[entry.0] = pdf_text_codepoints_of_tounicode_bytes_or_charcode(
entry.1,
entry.0,
)
}
}
values
}
///|
fn pdf_text_external_cmap_lookup(
parsed : PdfParsedCMap,
) -> PdfTextExternalCMapLookup {
{
cid_map: pdf_text_cmap_cid_lookup_map(parsed.cid_map),
notdef_map: pdf_text_cmap_cid_lookup_map(parsed.notdef_map),
map: pdf_text_tounicode_codepoints_lookup_map(parsed.map),
}
}
///|
fn pdf_text_reverse_lookup_tounicode_charcode(
tounicode : ArrayView[(Int, PdfBytes)],
codepoint : Int,
shadow_first : ArrayView[(Int, Int)],
shadow_second : ArrayView[(Int, Int)],
) -> Int? {
for entry in tounicode {
try pdf_codepoints_of_utf16be(entry.1) catch {
_ => ()
} noraise {
[single] if single == codepoint &&
!pdf_text_cmap_has_charcode_in_any(shadow_first, shadow_second, entry.0) =>
break Some(entry.0)
_ => ()
}
} nobreak {
None
}
}
///|
fn pdf_text_standard_control_glyphname(code : Int) -> PdfName? {
match code {
9 => Some(pdf_text_glyph_control_ht_name)
10 => Some(pdf_text_glyph_control_lf_name)
12 => Some(pdf_text_glyph_control_ff_name)
13 => Some(pdf_text_glyph_control_cr_name)
_ => None
}
}
///|
fn pdf_text_basic_latin_glyphname(
code : Int,
standard_quotes : Bool,
) -> PdfName? {
pdf_text_cached_basic_latin_glyphname(code, standard_quotes)
}
///|
fn pdf_text_standard_glyphname(code : Int) -> PdfName? {
match pdf_text_standard_control_glyphname(code) {
Some(name) => Some(name)
None =>
match pdf_text_basic_latin_glyphname(code, true) {
Some(name) => Some(name)
None =>
match code {
0xA1 => Some(pdf_text_name("/exclamdown"))
0xA2 => Some(pdf_text_name("/cent"))
0xA3 => Some(pdf_text_name("/sterling"))
0xA4 => Some(pdf_text_name("/fraction"))
0xA5 => Some(pdf_text_name("/yen"))
0xA6 => Some(pdf_text_name("/florin"))
0xA7 => Some(pdf_text_name("/section"))
0xA8 => Some(pdf_text_name("/currency"))
0xA9 => Some(pdf_text_name("/quotesingle"))
0xAA => Some(pdf_text_name("/quotedblleft"))
0xAB => Some(pdf_text_name("/guillemotleft"))
0xAC => Some(pdf_text_name("/guilsinglleft"))
0xAD => Some(pdf_text_name("/guilsinglright"))
0xAE => Some(pdf_text_name("/fi"))
0xAF => Some(pdf_text_name("/fl"))
0xB1 => Some(pdf_text_name("/endash"))
0xB2 => Some(pdf_text_name("/dagger"))
0xB3 => Some(pdf_text_name("/daggerdbl"))
0xB4 => Some(pdf_text_name("/periodcentered"))
0xB6 => Some(pdf_text_name("/paragraph"))
0xB7 => Some(pdf_text_name("/bullet"))
0xB8 => Some(pdf_text_name("/quotesinglbase"))
0xB9 => Some(pdf_text_name("/quotedblbase"))
0xBA => Some(pdf_text_name("/quotedblright"))
0xBB => Some(pdf_text_name("/guillemotright"))
0xBC => Some(pdf_text_name("/ellipsis"))
0xBD => Some(pdf_text_name("/perthousand"))
0xBF => Some(pdf_text_name("/questiondown"))
0xC1 => Some(pdf_text_name("/grave"))
0xC2 => Some(pdf_text_name("/acute"))
0xC3 => Some(pdf_text_name("/circumflex"))
0xC4 => Some(pdf_text_name("/tilde"))
0xC5 => Some(pdf_text_name("/macron"))
0xC6 => Some(pdf_text_name("/breve"))
0xC7 => Some(pdf_text_name("/dotaccent"))
0xC8 => Some(pdf_text_name("/dieresis"))
0xCA => Some(pdf_text_name("/ring"))
0xCB => Some(pdf_text_name("/cedilla"))
0xCD => Some(pdf_text_name("/hungarumlaut"))
0xCE => Some(pdf_text_name("/ogonek"))
0xCF => Some(pdf_text_name("/caron"))
0xD0 => Some(pdf_text_name("/emdash"))
0xE1 => Some(pdf_text_name("/AE"))
0xE3 => Some(pdf_text_name("/ordfeminine"))
0xE8 => Some(pdf_text_name("/Lslash"))
0xE9 => Some(pdf_text_name("/Oslash"))
0xEA => Some(pdf_text_name("/OE"))
0xEB => Some(pdf_text_name("/ordmasculine"))
0xF1 => Some(pdf_text_name("/ae"))
0xF5 => Some(pdf_text_name("/dotlessi"))
0xF8 => Some(pdf_text_name("/lslash"))
0xFA => Some(pdf_text_name("/oe"))
0xFB => Some(pdf_text_name("/germandbls"))
_ => None
}
}
}
}
///|
fn pdf_text_macroman_glyphname(code : Int) -> PdfName? {
match pdf_text_basic_latin_glyphname(code, false) {
Some(name) => Some(name)
None =>
match code {
0x80 => Some(pdf_text_name("/Adieresis"))
0x81 => Some(pdf_text_name("/Aring"))
0x82 => Some(pdf_text_name("/Ccedilla"))
0x83 => Some(pdf_text_name("/Eacute"))
0x84 => Some(pdf_text_name("/Ntilde"))
0x85 => Some(pdf_text_name("/Odieresis"))
0x86 => Some(pdf_text_name("/Udieresis"))
0x87 => Some(pdf_text_name("/aacute"))
0x88 => Some(pdf_text_name("/agrave"))
0x89 => Some(pdf_text_name("/acircumflex"))
0x8A => Some(pdf_text_name("/adieresis"))
0x8B => Some(pdf_text_name("/atilde"))
0x8C => Some(pdf_text_name("/aring"))
0x8D => Some(pdf_text_name("/ccedilla"))
0x8E => Some(pdf_text_name("/eacute"))
0x8F => Some(pdf_text_name("/egrave"))
0x90 => Some(pdf_text_name("/ecircumflex"))
0x91 => Some(pdf_text_name("/edieresis"))
0x92 => Some(pdf_text_name("/iacute"))
0x93 => Some(pdf_text_name("/igrave"))
0x94 => Some(pdf_text_name("/icircumflex"))
0x95 => Some(pdf_text_name("/idieresis"))
0x96 => Some(pdf_text_name("/ntilde"))
0x97 => Some(pdf_text_name("/oacute"))
0x98 => Some(pdf_text_name("/ograve"))
0x99 => Some(pdf_text_name("/ocircumflex"))
0x9A => Some(pdf_text_name("/odieresis"))
0x9B => Some(pdf_text_name("/otilde"))
0x9C => Some(pdf_text_name("/uacute"))
0x9D => Some(pdf_text_name("/ugrave"))
0x9E => Some(pdf_text_name("/ucircumflex"))
0x9F => Some(pdf_text_name("/udieresis"))
0xA0 => Some(pdf_text_name("/dagger"))
0xA1 => Some(pdf_text_name("/degree"))
0xA2 => Some(pdf_text_name("/cent"))
0xA3 => Some(pdf_text_name("/sterling"))
0xA4 => Some(pdf_text_name("/section"))
0xA5 => Some(pdf_text_name("/bullet"))
0xA6 => Some(pdf_text_name("/paragraph"))
0xA7 => Some(pdf_text_name("/germandbls"))
0xA8 => Some(pdf_text_name("/registered"))
0xA9 => Some(pdf_text_name("/copyright"))
0xAA => Some(pdf_text_name("/trademark"))
0xAB => Some(pdf_text_name("/acute"))
0xAC => Some(pdf_text_name("/dieresis"))
0xAE => Some(pdf_text_name("/AE"))
0xAF => Some(pdf_text_name("/Oslash"))
0xB1 => Some(pdf_text_name("/plusminus"))
0xB4 => Some(pdf_text_name("/yen"))
0xB5 => Some(pdf_text_name("/mu"))
0xBB => Some(pdf_text_name("/ordfeminine"))
0xBC => Some(pdf_text_name("/ordmasculine"))
0xBE => Some(pdf_text_name("/ae"))
0xBF => Some(pdf_text_name("/oslash"))
0xC0 => Some(pdf_text_name("/questiondown"))
0xC1 => Some(pdf_text_name("/exclamdown"))
0xC2 => Some(pdf_text_name("/logicalnot"))
0xC4 => Some(pdf_text_name("/florin"))
0xC7 => Some(pdf_text_name("/guillemotleft"))
0xC8 => Some(pdf_text_name("/guillemotright"))
0xC9 => Some(pdf_text_name("/ellipsis"))
0xCA => Some(pdf_text_glyph_space_name)
0xCB => Some(pdf_text_name("/Agrave"))
0xCC => Some(pdf_text_name("/Atilde"))
0xCD => Some(pdf_text_name("/Otilde"))
0xCE => Some(pdf_text_name("/OE"))
0xCF => Some(pdf_text_name("/oe"))
0xD0 => Some(pdf_text_name("/endash"))
0xD1 => Some(pdf_text_name("/emdash"))
0xD2 => Some(pdf_text_name("/quotedblleft"))
0xD3 => Some(pdf_text_name("/quotedblright"))
0xD4 => Some(pdf_text_name("/quoteleft"))
0xD5 => Some(pdf_text_name("/quoteright"))
0xD6 => Some(pdf_text_name("/divide"))
0xD8 => Some(pdf_text_name("/ydieresis"))
0xD9 => Some(pdf_text_name("/Ydieresis"))
0xDA => Some(pdf_text_name("/fraction"))
0xDB => Some(pdf_text_name("/currency"))
0xDC => Some(pdf_text_name("/guilsinglleft"))
0xDD => Some(pdf_text_name("/guilsinglright"))
0xDE => Some(pdf_text_name("/fi"))
0xDF => Some(pdf_text_name("/fl"))
0xE0 => Some(pdf_text_name("/daggerdbl"))
0xE1 => Some(pdf_text_name("/periodcentered"))
0xE2 => Some(pdf_text_name("/quotesinglbase"))
0xE3 => Some(pdf_text_name("/quotedblbase"))
0xE4 => Some(pdf_text_name("/perthousand"))
0xE5 => Some(pdf_text_name("/Acircumflex"))
0xE6 => Some(pdf_text_name("/Ecircumflex"))
0xE7 => Some(pdf_text_name("/Aacute"))
0xE8 => Some(pdf_text_name("/Edieresis"))
0xE9 => Some(pdf_text_name("/Egrave"))
0xEA => Some(pdf_text_name("/Iacute"))
0xEB => Some(pdf_text_name("/Icircumflex"))
0xEC => Some(pdf_text_name("/Idieresis"))
0xED => Some(pdf_text_name("/Igrave"))
0xEE => Some(pdf_text_name("/Oacute"))
0xEF => Some(pdf_text_name("/Ocircumflex"))
0xF1 => Some(pdf_text_name("/Ograve"))
0xF2 => Some(pdf_text_name("/Uacute"))
0xF3 => Some(pdf_text_name("/Ucircumflex"))
0xF4 => Some(pdf_text_name("/Ugrave"))
0xF5 => Some(pdf_text_name("/dotlessi"))
0xF6 => Some(pdf_text_name("/circumflex"))
0xF7 => Some(pdf_text_name("/tilde"))
0xF8 => Some(pdf_text_name("/macron"))
0xF9 => Some(pdf_text_name("/breve"))
0xFA => Some(pdf_text_name("/dotaccent"))
0xFB => Some(pdf_text_name("/ring"))
0xFC => Some(pdf_text_name("/cedilla"))
0xFD => Some(pdf_text_name("/hungarumlaut"))
0xFE => Some(pdf_text_name("/ogonek"))
0xFF => Some(pdf_text_name("/caron"))
_ => None
}
}
}
///|
fn pdf_text_winansi_glyphname(code : Int) -> PdfName? {
match pdf_text_basic_latin_glyphname(code, false) {
Some(name) => Some(name)
None =>
match code {
0x80 => Some(pdf_text_name("/Euro"))
0x82 => Some(pdf_text_name("/quotesinglbase"))
0x83 => Some(pdf_text_name("/florin"))
0x84 => Some(pdf_text_name("/quotedblbase"))
0x85 => Some(pdf_text_name("/ellipsis"))
0x86 => Some(pdf_text_name("/dagger"))
0x87 => Some(pdf_text_name("/daggerdbl"))
0x88 => Some(pdf_text_name("/circumflex"))
0x89 => Some(pdf_text_name("/perthousand"))
0x8A => Some(pdf_text_name("/Scaron"))
0x8B => Some(pdf_text_name("/guilsinglleft"))
0x8C => Some(pdf_text_name("/OE"))
0x8E => Some(pdf_text_name("/Zcaron"))
0x91 => Some(pdf_text_name("/quoteleft"))
0x92 => Some(pdf_text_name("/quoteright"))
0x93 => Some(pdf_text_name("/quotedblleft"))
0x94 => Some(pdf_text_name("/quotedblright"))
0x95 => Some(pdf_text_name("/bullet"))
0x96 => Some(pdf_text_name("/endash"))
0x97 => Some(pdf_text_name("/emdash"))
0x98 => Some(pdf_text_name("/tilde"))
0x99 => Some(pdf_text_name("/trademark"))
0x9A => Some(pdf_text_name("/scaron"))
0x9B => Some(pdf_text_name("/guilsinglright"))
0x9C => Some(pdf_text_name("/oe"))
0x9E => Some(pdf_text_name("/zcaron"))
0x9F => Some(pdf_text_name("/Ydieresis"))
0xA0 => Some(pdf_text_glyph_space_name)
0xA1 => Some(pdf_text_name("/exclamdown"))
0xA2 => Some(pdf_text_name("/cent"))
0xA3 => Some(pdf_text_name("/sterling"))
0xA4 => Some(pdf_text_name("/currency"))
0xA5 => Some(pdf_text_name("/yen"))
0xA6 => Some(pdf_text_name("/brokenbar"))
0xA7 => Some(pdf_text_name("/section"))
0xA8 => Some(pdf_text_name("/dieresis"))
0xA9 => Some(pdf_text_name("/copyright"))
0xAA => Some(pdf_text_name("/ordfeminine"))
0xAB => Some(pdf_text_name("/guillemotleft"))
0xAC => Some(pdf_text_name("/logicalnot"))
0xAD => Some(pdf_text_name("/hyphen"))
0xAE => Some(pdf_text_name("/registered"))
0xAF => Some(pdf_text_name("/macron"))
0xB0 => Some(pdf_text_name("/degree"))
0xB1 => Some(pdf_text_name("/plusminus"))
0xB2 => Some(pdf_text_name("/twosuperior"))
0xB3 => Some(pdf_text_name("/threesuperior"))
0xB4 => Some(pdf_text_name("/acute"))
0xB5 => Some(pdf_text_name("/mu"))
0xB6 => Some(pdf_text_name("/paragraph"))
0xB7 => Some(pdf_text_name("/periodcentered"))
0xB8 => Some(pdf_text_name("/cedilla"))
0xB9 => Some(pdf_text_name("/onesuperior"))
0xBA => Some(pdf_text_name("/ordmasculine"))
0xBB => Some(pdf_text_name("/guillemotright"))
0xBC => Some(pdf_text_name("/onequarter"))
0xBD => Some(pdf_text_name("/onehalf"))
0xBE => Some(pdf_text_name("/threequarters"))
0xBF => Some(pdf_text_name("/questiondown"))
0xC0 => Some(pdf_text_name("/Agrave"))
0xC1 => Some(pdf_text_name("/Aacute"))
0xC2 => Some(pdf_text_name("/Acircumflex"))
0xC3 => Some(pdf_text_name("/Atilde"))
0xC4 => Some(pdf_text_name("/Adieresis"))
0xC5 => Some(pdf_text_name("/Aring"))
0xC6 => Some(pdf_text_name("/AE"))
0xC7 => Some(pdf_text_name("/Ccedilla"))
0xC8 => Some(pdf_text_name("/Egrave"))
0xC9 => Some(pdf_text_name("/Eacute"))
0xCA => Some(pdf_text_name("/Ecircumflex"))
0xCB => Some(pdf_text_name("/Edieresis"))
0xCC => Some(pdf_text_name("/Igrave"))
0xCD => Some(pdf_text_name("/Iacute"))
0xCE => Some(pdf_text_name("/Icircumflex"))
0xCF => Some(pdf_text_name("/Idieresis"))
0xD0 => Some(pdf_text_name("/Eth"))
0xD1 => Some(pdf_text_name("/Ntilde"))
0xD2 => Some(pdf_text_name("/Ograve"))
0xD3 => Some(pdf_text_name("/Oacute"))
0xD4 => Some(pdf_text_name("/Ocircumflex"))
0xD5 => Some(pdf_text_name("/Otilde"))
0xD6 => Some(pdf_text_name("/Odieresis"))
0xD7 => Some(pdf_text_name("/multiply"))
0xD8 => Some(pdf_text_name("/Oslash"))
0xD9 => Some(pdf_text_name("/Ugrave"))
0xDA => Some(pdf_text_name("/Uacute"))
0xDB => Some(pdf_text_name("/Ucircumflex"))
0xDC => Some(pdf_text_name("/Udieresis"))
0xDD => Some(pdf_text_name("/Yacute"))
0xDE => Some(pdf_text_name("/Thorn"))
0xDF => Some(pdf_text_name("/germandbls"))
0xE0 => Some(pdf_text_name("/agrave"))
0xE1 => Some(pdf_text_name("/aacute"))
0xE2 => Some(pdf_text_name("/acircumflex"))
0xE3 => Some(pdf_text_name("/atilde"))
0xE4 => Some(pdf_text_name("/adieresis"))
0xE5 => Some(pdf_text_name("/aring"))
0xE6 => Some(pdf_text_name("/ae"))
0xE7 => Some(pdf_text_name("/ccedilla"))
0xE8 => Some(pdf_text_name("/egrave"))
0xE9 => Some(pdf_text_name("/eacute"))
0xEA => Some(pdf_text_name("/ecircumflex"))
0xEB => Some(pdf_text_name("/edieresis"))
0xEC => Some(pdf_text_name("/igrave"))
0xED => Some(pdf_text_name("/iacute"))
0xEE => Some(pdf_text_name("/icircumflex"))
0xEF => Some(pdf_text_name("/idieresis"))
0xF0 => Some(pdf_text_name("/eth"))
0xF1 => Some(pdf_text_name("/ntilde"))
0xF2 => Some(pdf_text_name("/ograve"))
0xF3 => Some(pdf_text_name("/oacute"))
0xF4 => Some(pdf_text_name("/ocircumflex"))
0xF5 => Some(pdf_text_name("/otilde"))
0xF6 => Some(pdf_text_name("/odieresis"))
0xF7 => Some(pdf_text_name("/divide"))
0xF8 => Some(pdf_text_name("/oslash"))
0xF9 => Some(pdf_text_name("/ugrave"))
0xFA => Some(pdf_text_name("/uacute"))
0xFB => Some(pdf_text_name("/ucircumflex"))
0xFC => Some(pdf_text_name("/udieresis"))
0xFD => Some(pdf_text_name("/yacute"))
0xFE => Some(pdf_text_name("/thorn"))
0xFF => Some(pdf_text_name("/ydieresis"))
_ => None
}
}
}
///|
fn pdf_text_macexpert_glyphname(code : Int) -> PdfName? {
match code {
0x20 => Some(pdf_text_glyph_space_name)
0x21 => Some(pdf_text_name("/exclamsmall"))
0x22 => Some(pdf_text_name("/Hungarumlautsmall"))
0x23 => Some(pdf_text_name("/centoldstyle"))
0x24 => Some(pdf_text_name("/dollaroldstyle"))
0x26 => Some(pdf_text_name("/ampersandsmall"))
0x27 => Some(pdf_text_name("/Acutesmall"))
0x28 => Some(pdf_text_name("/parenleftsuperior"))
0x29 => Some(pdf_text_name("/parenrightsuperior"))
0x2A => Some(pdf_text_name("/twodotenleader"))
0x2B => Some(pdf_text_name("/onedotenleader"))
0x2C => Some(pdf_text_name("/comma"))
0x2D => Some(pdf_text_name("/hyphen"))
0x2E => Some(pdf_text_name("/period"))
0x2F => Some(pdf_text_name("/fraction"))
0x30 => Some(pdf_text_name("/zerooldstyle"))
0x31 => Some(pdf_text_name("/oneoldstyle"))
0x32 => Some(pdf_text_name("/twooldstyle"))
0x33 => Some(pdf_text_name("/threeoldstyle"))
0x34 => Some(pdf_text_name("/fouroldstyle"))
0x35 => Some(pdf_text_name("/fiveoldstyle"))
0x36 => Some(pdf_text_name("/sixoldstyle"))
0x37 => Some(pdf_text_name("/sevenoldstyle"))
0x38 => Some(pdf_text_name("/eightoldstyle"))
0x39 => Some(pdf_text_name("/nineoldstyle"))
0x3A => Some(pdf_text_name("/colon"))
0x3B => Some(pdf_text_name("/semicolon"))
0x3D => Some(pdf_text_name("/threequartersemdash"))
0x3F => Some(pdf_text_name("/questionsmall"))
0x44 => Some(pdf_text_name("/Ethsmall"))
0x47 => Some(pdf_text_name("/onequarter"))
0x48 => Some(pdf_text_name("/onehalf"))
0x49 => Some(pdf_text_name("/threequarters"))
0x4A => Some(pdf_text_name("/oneeighth"))
0x4B => Some(pdf_text_name("/threeeighths"))
0x4C => Some(pdf_text_name("/fiveeighths"))
0x4D => Some(pdf_text_name("/seveneighths"))
0x4E => Some(pdf_text_name("/onethird"))
0x4F => Some(pdf_text_name("/twothirds"))
0x56 => Some(pdf_text_name("/ff"))
0x57 => Some(pdf_text_name("/fi"))
0x58 => Some(pdf_text_name("/fl"))
0x59 => Some(pdf_text_name("/ffi"))
0x5A => Some(pdf_text_name("/ffl"))
0x5B => Some(pdf_text_name("/parenleftinferior"))
0x5D => Some(pdf_text_name("/parenrightinferior"))
0x5E => Some(pdf_text_name("/Circumflexsmall"))
0x5F => Some(pdf_text_name("/hypheninferior"))
0x60 => Some(pdf_text_name("/Gravesmall"))
0x61 => Some(pdf_text_name("/Asmall"))
0x62 => Some(pdf_text_name("/Bsmall"))
0x63 => Some(pdf_text_name("/Csmall"))
0x64 => Some(pdf_text_name("/Dsmall"))
0x65 => Some(pdf_text_name("/Esmall"))
0x66 => Some(pdf_text_name("/Fsmall"))
0x67 => Some(pdf_text_name("/Gsmall"))
0x68 => Some(pdf_text_name("/Hsmall"))
0x69 => Some(pdf_text_name("/Ismall"))
0x6A => Some(pdf_text_name("/Jsmall"))
0x6B => Some(pdf_text_name("/Ksmall"))
0x6C => Some(pdf_text_name("/Lsmall"))
0x6D => Some(pdf_text_name("/Msmall"))
0x6E => Some(pdf_text_name("/Nsmall"))
0x6F => Some(pdf_text_name("/Osmall"))
0x70 => Some(pdf_text_name("/Psmall"))
0x71 => Some(pdf_text_name("/Qsmall"))
0x72 => Some(pdf_text_name("/Rsmall"))
0x73 => Some(pdf_text_name("/Ssmall"))
0x74 => Some(pdf_text_name("/Tsmall"))
0x75 => Some(pdf_text_name("/Usmall"))
0x76 => Some(pdf_text_name("/Vsmall"))
0x77 => Some(pdf_text_name("/Wsmall"))
0x78 => Some(pdf_text_name("/Xsmall"))
0x79 => Some(pdf_text_name("/Ysmall"))
0x7A => Some(pdf_text_name("/Zsmall"))
0x7B => Some(pdf_text_name("/colonmonetary"))
0x7C => Some(pdf_text_name("/onefitted"))
0x7D => Some(pdf_text_name("/rupiah"))
0x7E => Some(pdf_text_name("/Tildesmall"))
0x81 => Some(pdf_text_name("/asuperior"))
0x82 => Some(pdf_text_name("/centsuperior"))
0x87 => Some(pdf_text_name("/Aacutesmall"))
0x88 => Some(pdf_text_name("/Agravesmall"))
0x89 => Some(pdf_text_name("/Acircumflexsmall"))
0x8A => Some(pdf_text_name("/Adieresissmall"))
0x8B => Some(pdf_text_name("/Atildesmall"))
0x8C => Some(pdf_text_name("/Aringsmall"))
0x8D => Some(pdf_text_name("/Ccedillasmall"))
0x8E => Some(pdf_text_name("/Eacutesmall"))
0x8F => Some(pdf_text_name("/Egravesmall"))
0x90 => Some(pdf_text_name("/Ecircumflexsmall"))
0x91 => Some(pdf_text_name("/Edieresissmall"))
0x92 => Some(pdf_text_name("/Iacutesmall"))
0x93 => Some(pdf_text_name("/Igravesmall"))
0x94 => Some(pdf_text_name("/Icircumflexsmall"))
0x95 => Some(pdf_text_name("/Idieresissmall"))
0x96 => Some(pdf_text_name("/Ntildesmall"))
0x97 => Some(pdf_text_name("/Oacutesmall"))
0x98 => Some(pdf_text_name("/Ogravesmall"))
0x99 => Some(pdf_text_name("/Ocircumflexsmall"))
0x9A => Some(pdf_text_name("/Odieresissmall"))
0x9B => Some(pdf_text_name("/Otildesmall"))
0x9C => Some(pdf_text_name("/Uacutesmall"))
0x9D => Some(pdf_text_name("/Ugravesmall"))
0x9E => Some(pdf_text_name("/Ucircumflexsmall"))
0x9F => Some(pdf_text_name("/Udieresissmall"))
0xA1 => Some(pdf_text_name("/eightsuperior"))
0xA2 => Some(pdf_text_name("/fourinferior"))
0xA3 => Some(pdf_text_name("/threeinferior"))
0xA4 => Some(pdf_text_name("/sixinferior"))
0xA5 => Some(pdf_text_name("/eightinferior"))
0xA6 => Some(pdf_text_name("/seveninferior"))
0xA7 => Some(pdf_text_name("/Scaronsmall"))
0xA9 => Some(pdf_text_name("/centinferior"))
0xAA => Some(pdf_text_name("/twoinferior"))
0xAC => Some(pdf_text_name("/Dieresissmall"))
0xAE => Some(pdf_text_name("/Caronsmall"))
0xAF => Some(pdf_text_name("/osuperior"))
0xB0 => Some(pdf_text_name("/fiveinferior"))
0xB2 => Some(pdf_text_name("/commainferior"))
0xB3 => Some(pdf_text_name("/periodinferior"))
0xB4 => Some(pdf_text_name("/Yacutesmall"))
0xB6 => Some(pdf_text_name("/dollarinferior"))
0xB9 => Some(pdf_text_name("/Thornsmall"))
0xBB => Some(pdf_text_name("/nineinferior"))
0xBC => Some(pdf_text_name("/zeroinferior"))
0xBD => Some(pdf_text_name("/Zcaronsmall"))
0xBE => Some(pdf_text_name("/AEsmall"))
0xBF => Some(pdf_text_name("/Oslashsmall"))
0xC0 => Some(pdf_text_name("/questiondownsmall"))
0xC1 => Some(pdf_text_name("/oneinferior"))
0xC2 => Some(pdf_text_name("/Lslashsmall"))
0xC9 => Some(pdf_text_name("/Cedillasmall"))
0xCF => Some(pdf_text_name("/OEsmall"))
0xD0 => Some(pdf_text_name("/figuredash"))
0xD6 => Some(pdf_text_name("/exclamdownsmall"))
0xD8 => Some(pdf_text_name("/Ydieresissmall"))
0xDA => Some(pdf_text_name("/onesuperior"))
0xDB => Some(pdf_text_name("/twosuperior"))
0xDC => Some(pdf_text_name("/threesuperior"))
0xDD => Some(pdf_text_name("/foursuperior"))
0xDE => Some(pdf_text_name("/fivesuperior"))
0xDF => Some(pdf_text_name("/sixsuperior"))
0xE0 => Some(pdf_text_name("/sevensuperior"))
0xE1 => Some(pdf_text_name("/ninesuperior"))
0xE2 => Some(pdf_text_name("/zerosuperior"))
0xE4 => Some(pdf_text_name("/esuperior"))
0xE5 => Some(pdf_text_name("/rsuperior"))
0xE6 => Some(pdf_text_name("/tsuperior"))
0xE9 => Some(pdf_text_name("/isuperior"))
0xEA => Some(pdf_text_name("/ssuperior"))
0xEB => Some(pdf_text_name("/dsuperior"))
0xF1 => Some(pdf_text_name("/lsuperior"))
0xF2 => Some(pdf_text_name("/Ogoneksmall"))
0xF3 => Some(pdf_text_name("/Brevesmall"))
0xF4 => Some(pdf_text_name("/Macronsmall"))
0xF5 => Some(pdf_text_name("/bsuperior"))
0xF6 => Some(pdf_text_name("/nsuperior"))
0xF7 => Some(pdf_text_name("/msuperior"))
0xF8 => Some(pdf_text_name("/commasuperior"))
0xF9 => Some(pdf_text_name("/periodsuperior"))
0xFA => Some(pdf_text_name("/Dotaccentsmall"))
0xFB => Some(pdf_text_name("/Ringsmall"))
_ => None
}
}
///|
fn pdf_text_symbol_glyphname(code : Int) -> PdfName? {
match code {
0x20 => Some(pdf_text_glyph_space_name)
0x21 => Some(pdf_text_name("/exclam"))
0x22 => Some(pdf_text_name("/universal"))
0x23 => Some(pdf_text_name("/numbersign"))
0x24 => Some(pdf_text_name("/existential"))
0x25 => Some(pdf_text_name("/percent"))
0x26 => Some(pdf_text_name("/ampersand"))
0x27 => Some(pdf_text_name("/suchthat"))
0x28 => Some(pdf_text_name("/parenleft"))
0x29 => Some(pdf_text_name("/parenright"))
0x2A => Some(pdf_text_name("/asteriskmath"))
0x2B => Some(pdf_text_name("/plus"))
0x2C => Some(pdf_text_name("/comma"))
0x2D => Some(pdf_text_name("/minus"))
0x2E => Some(pdf_text_name("/period"))
0x2F => Some(pdf_text_name("/slash"))
0x30 => Some(pdf_text_name("/zero"))
0x31 => Some(pdf_text_name("/one"))
0x32 => Some(pdf_text_name("/two"))
0x33 => Some(pdf_text_name("/three"))
0x34 => Some(pdf_text_name("/four"))
0x35 => Some(pdf_text_name("/five"))
0x36 => Some(pdf_text_name("/six"))
0x37 => Some(pdf_text_name("/seven"))
0x38 => Some(pdf_text_name("/eight"))
0x39 => Some(pdf_text_name("/nine"))
0x3A => Some(pdf_text_name("/colon"))
0x3B => Some(pdf_text_name("/semicolon"))
0x3C => Some(pdf_text_name("/less"))
0x3D => Some(pdf_text_name("/equal"))
0x3E => Some(pdf_text_name("/greater"))
0x3F => Some(pdf_text_name("/question"))
0x40 => Some(pdf_text_name("/congruent"))
0x41 => Some(pdf_text_name("/Alpha"))
0x42 => Some(pdf_text_name("/Beta"))
0x43 => Some(pdf_text_name("/Chi"))
0x44 => Some(pdf_text_name("/Delta"))
0x45 => Some(pdf_text_name("/Epsilon"))
0x46 => Some(pdf_text_name("/Phi"))
0x47 => Some(pdf_text_name("/Gamma"))
0x48 => Some(pdf_text_name("/Eta"))
0x49 => Some(pdf_text_name("/Iota"))
0x4A => Some(pdf_text_name("/theta1"))
0x4B => Some(pdf_text_name("/Kappa"))
0x4C => Some(pdf_text_name("/Lambda"))
0x4D => Some(pdf_text_name("/Mu"))
0x4E => Some(pdf_text_name("/Nu"))
0x4F => Some(pdf_text_name("/Omicron"))
0x50 => Some(pdf_text_name("/Pi"))
0x51 => Some(pdf_text_name("/Theta"))
0x52 => Some(pdf_text_name("/Rho"))
0x53 => Some(pdf_text_name("/Sigma"))
0x54 => Some(pdf_text_name("/Tau"))
0x55 => Some(pdf_text_name("/Upsilon"))
0x56 => Some(pdf_text_name("/sigma1"))
0x57 => Some(pdf_text_name("/Omega"))
0x58 => Some(pdf_text_name("/Xi"))
0x59 => Some(pdf_text_name("/Psi"))
0x5A => Some(pdf_text_name("/Zeta"))
0x5B => Some(pdf_text_name("/bracketleft"))
0x5C => Some(pdf_text_name("/therefore"))
0x5D => Some(pdf_text_name("/bracketright"))
0x5E => Some(pdf_text_name("/perpendicular"))
0x5F => Some(pdf_text_name("/underscore"))
0x60 => Some(pdf_text_name("/radicalex"))
0x61 => Some(pdf_text_name("/alpha"))
0x62 => Some(pdf_text_name("/beta"))
0x63 => Some(pdf_text_name("/chi"))
0x64 => Some(pdf_text_name("/delta"))
0x65 => Some(pdf_text_name("/epsilon"))
0x66 => Some(pdf_text_name("/phi"))
0x67 => Some(pdf_text_name("/gamma"))
0x68 => Some(pdf_text_name("/eta"))
0x69 => Some(pdf_text_name("/iota"))
0x6A => Some(pdf_text_name("/phi1"))
0x6B => Some(pdf_text_name("/kappa"))
0x6C => Some(pdf_text_name("/lambda"))
0x6D => Some(pdf_text_name("/mu"))
0x6E => Some(pdf_text_name("/nu"))
0x6F => Some(pdf_text_name("/omicron"))
0x70 => Some(pdf_text_name("/pi"))
0x71 => Some(pdf_text_name("/theta"))
0x72 => Some(pdf_text_name("/rho"))
0x73 => Some(pdf_text_name("/sigma"))
0x74 => Some(pdf_text_name("/tau"))
0x75 => Some(pdf_text_name("/upsilon"))
0x76 => Some(pdf_text_name("/omega1"))
0x77 => Some(pdf_text_name("/omega"))
0x78 => Some(pdf_text_name("/xi"))
0x79 => Some(pdf_text_name("/psi"))
0x7A => Some(pdf_text_name("/zeta"))
0x7B => Some(pdf_text_name("/braceleft"))
0x7C => Some(pdf_text_name("/bar"))
0x7D => Some(pdf_text_name("/braceright"))
0x7E => Some(pdf_text_name("/similar"))
0xA0 => Some(pdf_text_name("/Euro"))
0xA1 => Some(pdf_text_name("/Upsilon1"))
0xA2 => Some(pdf_text_name("/minute"))
0xA3 => Some(pdf_text_name("/lessequal"))
0xA4 => Some(pdf_text_name("/fraction"))
0xA5 => Some(pdf_text_name("/infinity"))
0xA6 => Some(pdf_text_name("/florin"))
0xA7 => Some(pdf_text_name("/club"))
0xA8 => Some(pdf_text_name("/diamond"))
0xA9 => Some(pdf_text_name("/heart"))
0xAA => Some(pdf_text_name("/spade"))
0xAB => Some(pdf_text_name("/arrowboth"))
0xAC => Some(pdf_text_name("/arrowleft"))
0xAD => Some(pdf_text_name("/arrowup"))
0xAE => Some(pdf_text_name("/arrowright"))
0xAF => Some(pdf_text_name("/arrowdown"))
0xB0 => Some(pdf_text_name("/degree"))
0xB1 => Some(pdf_text_name("/plusminus"))
0xB2 => Some(pdf_text_name("/second"))
0xB3 => Some(pdf_text_name("/greaterequal"))
0xB4 => Some(pdf_text_name("/multiply"))
0xB5 => Some(pdf_text_name("/proportional"))
0xB6 => Some(pdf_text_name("/partialdiff"))
0xB7 => Some(pdf_text_name("/bullet"))
0xB8 => Some(pdf_text_name("/divide"))
0xB9 => Some(pdf_text_name("/notequal"))
0xBA => Some(pdf_text_name("/equivalence"))
0xBB => Some(pdf_text_name("/approxequal"))
0xBC => Some(pdf_text_name("/ellipsis"))
0xBD => Some(pdf_text_name("/arrowvertex"))
0xBE => Some(pdf_text_name("/arrowhorizex"))
0xBF => Some(pdf_text_name("/carriagereturn"))
0xC0 => Some(pdf_text_name("/aleph"))
0xC1 => Some(pdf_text_name("/Ifraktur"))
0xC2 => Some(pdf_text_name("/Rfraktur"))
0xC3 => Some(pdf_text_name("/weierstrass"))
0xC4 => Some(pdf_text_name("/circlemultiply"))
0xC5 => Some(pdf_text_name("/circleplus"))
0xC6 => Some(pdf_text_name("/emptyset"))
0xC7 => Some(pdf_text_name("/intersection"))
0xC8 => Some(pdf_text_name("/union"))
0xC9 => Some(pdf_text_name("/propersuperset"))
0xCA => Some(pdf_text_name("/reflexsuperset"))
0xCB => Some(pdf_text_name("/notsubset"))
0xCC => Some(pdf_text_name("/propersubset"))
0xCD => Some(pdf_text_name("/reflexsubset"))
0xCE => Some(pdf_text_name("/element"))
0xCF => Some(pdf_text_name("/notelement"))
0xD0 => Some(pdf_text_name("/angle"))
0xD1 => Some(pdf_text_name("/gradient"))
0xD2 => Some(pdf_text_name("/registerserif"))
0xD3 => Some(pdf_text_name("/copyrightserif"))
0xD4 => Some(pdf_text_name("/trademarkserif"))
0xD5 => Some(pdf_text_name("/product"))
0xD6 => Some(pdf_text_name("/radical"))
0xD7 => Some(pdf_text_name("/dotmath"))
0xD8 => Some(pdf_text_name("/logicalnot"))
0xD9 => Some(pdf_text_name("/logicaland"))
0xDA => Some(pdf_text_name("/logicalor"))
0xDB => Some(pdf_text_name("/arrowdblboth"))
0xDC => Some(pdf_text_name("/arrowdblleft"))
0xDD => Some(pdf_text_name("/arrowdblup"))
0xDE => Some(pdf_text_name("/arrowdblright"))
0xDF => Some(pdf_text_name("/arrowdbldown"))
0xE0 => Some(pdf_text_name("/lozenge"))
0xE1 => Some(pdf_text_name("/angleleft"))
0xE2 => Some(pdf_text_name("/registersans"))
0xE3 => Some(pdf_text_name("/copyrightsans"))
0xE4 => Some(pdf_text_name("/trademarksans"))
0xE5 => Some(pdf_text_name("/summation"))
0xE6 => Some(pdf_text_name("/parenlefttp"))
0xE7 => Some(pdf_text_name("/parenleftex"))
0xE8 => Some(pdf_text_name("/parenleftbt"))
0xE9 => Some(pdf_text_name("/bracketlefttp"))
0xEA => Some(pdf_text_name("/bracketleftex"))
0xEB => Some(pdf_text_name("/bracketleftbt"))
0xEC => Some(pdf_text_name("/bracelefttp"))
0xED => Some(pdf_text_name("/braceleftmid"))
0xEE => Some(pdf_text_name("/braceleftbt"))
0xEF => Some(pdf_text_name("/braceex"))
0xF1 => Some(pdf_text_name("/angleright"))
0xF2 => Some(pdf_text_name("/integral"))
0xF3 => Some(pdf_text_name("/integraltp"))
0xF4 => Some(pdf_text_name("/integralex"))
0xF5 => Some(pdf_text_name("/integralbt"))
0xF6 => Some(pdf_text_name("/parenrighttp"))
0xF7 => Some(pdf_text_name("/parenrightex"))
0xF8 => Some(pdf_text_name("/parenrightbt"))
0xF9 => Some(pdf_text_name("/bracketrighttp"))
0xFA => Some(pdf_text_name("/bracketrightex"))
0xFB => Some(pdf_text_name("/bracketrightbt"))
0xFC => Some(pdf_text_name("/bracerighttp"))
0xFD => Some(pdf_text_name("/bracerightmid"))
0xFE => Some(pdf_text_name("/bracerightbt"))
_ => None
}
}
///|
fn pdf_text_zapfdingbats_glyphname(code : Int) -> PdfName? {
match code {
0x20 => Some(pdf_text_glyph_space_name)
0x21 => Some(pdf_text_name("/a1"))
0x22 => Some(pdf_text_name("/a2"))
0x23 => Some(pdf_text_name("/a202"))
0x24 => Some(pdf_text_name("/a3"))
0x25 => Some(pdf_text_name("/a4"))
0x26 => Some(pdf_text_name("/a5"))
0x27 => Some(pdf_text_name("/a119"))
0x28 => Some(pdf_text_name("/a118"))
0x29 => Some(pdf_text_name("/a117"))
0x2A => Some(pdf_text_name("/a11"))
0x2B => Some(pdf_text_name("/a12"))
0x2C => Some(pdf_text_name("/a13"))
0x2D => Some(pdf_text_name("/a14"))
0x2E => Some(pdf_text_name("/a15"))
0x2F => Some(pdf_text_name("/a16"))
0x30 => Some(pdf_text_name("/a105"))
0x31 => Some(pdf_text_name("/a17"))
0x32 => Some(pdf_text_name("/a18"))
0x33 => Some(pdf_text_name("/a19"))
0x34 => Some(pdf_text_name("/a20"))
0x35 => Some(pdf_text_name("/a21"))
0x36 => Some(pdf_text_name("/a22"))
0x37 => Some(pdf_text_name("/a23"))
0x38 => Some(pdf_text_name("/a24"))
0x39 => Some(pdf_text_name("/a25"))
0x3A => Some(pdf_text_name("/a26"))
0x3B => Some(pdf_text_name("/a27"))
0x3C => Some(pdf_text_name("/a28"))
0x3D => Some(pdf_text_name("/a6"))
0x3E => Some(pdf_text_name("/a7"))
0x3F => Some(pdf_text_name("/a8"))
0x40 => Some(pdf_text_name("/a9"))
0x41 => Some(pdf_text_name("/a10"))
0x42 => Some(pdf_text_name("/a29"))
0x43 => Some(pdf_text_name("/a30"))
0x44 => Some(pdf_text_name("/a31"))
0x45 => Some(pdf_text_name("/a32"))
0x46 => Some(pdf_text_name("/a33"))
0x47 => Some(pdf_text_name("/a34"))
0x48 => Some(pdf_text_name("/a35"))
0x49 => Some(pdf_text_name("/a36"))
0x4A => Some(pdf_text_name("/a37"))
0x4B => Some(pdf_text_name("/a38"))
0x4C => Some(pdf_text_name("/a39"))
0x4D => Some(pdf_text_name("/a40"))
0x4E => Some(pdf_text_name("/a41"))
0x4F => Some(pdf_text_name("/a42"))
0x50 => Some(pdf_text_name("/a43"))
0x51 => Some(pdf_text_name("/a44"))
0x52 => Some(pdf_text_name("/a45"))
0x53 => Some(pdf_text_name("/a46"))
0x54 => Some(pdf_text_name("/a47"))
0x55 => Some(pdf_text_name("/a48"))
0x56 => Some(pdf_text_name("/a49"))
0x57 => Some(pdf_text_name("/a50"))
0x58 => Some(pdf_text_name("/a51"))
0x59 => Some(pdf_text_name("/a52"))
0x5A => Some(pdf_text_name("/a53"))
0x5B => Some(pdf_text_name("/a54"))
0x5C => Some(pdf_text_name("/a55"))
0x5D => Some(pdf_text_name("/a56"))
0x5E => Some(pdf_text_name("/a57"))
0x5F => Some(pdf_text_name("/a58"))
0x60 => Some(pdf_text_name("/a59"))
0x61 => Some(pdf_text_name("/a60"))
0x62 => Some(pdf_text_name("/a61"))
0x63 => Some(pdf_text_name("/a62"))
0x64 => Some(pdf_text_name("/a63"))
0x65 => Some(pdf_text_name("/a64"))
0x66 => Some(pdf_text_name("/a65"))
0x67 => Some(pdf_text_name("/a66"))
0x68 => Some(pdf_text_name("/a67"))
0x69 => Some(pdf_text_name("/a68"))
0x6A => Some(pdf_text_name("/a69"))
0x6B => Some(pdf_text_name("/a70"))
0x6C => Some(pdf_text_name("/a71"))
0x6D => Some(pdf_text_name("/a72"))
0x6E => Some(pdf_text_name("/a73"))
0x6F => Some(pdf_text_name("/a74"))
0x70 => Some(pdf_text_name("/a203"))
0x71 => Some(pdf_text_name("/a75"))
0x72 => Some(pdf_text_name("/a204"))
0x73 => Some(pdf_text_name("/a76"))
0x74 => Some(pdf_text_name("/a77"))
0x75 => Some(pdf_text_name("/a78"))
0x76 => Some(pdf_text_name("/a79"))
0x77 => Some(pdf_text_name("/a81"))
0x78 => Some(pdf_text_name("/a82"))
0x79 => Some(pdf_text_name("/a83"))
0x7A => Some(pdf_text_name("/a84"))
0x7B => Some(pdf_text_name("/a97"))
0x7C => Some(pdf_text_name("/a98"))
0x7D => Some(pdf_text_name("/a99"))
0x7E => Some(pdf_text_name("/a100"))
0xA1 => Some(pdf_text_name("/a101"))
0xA2 => Some(pdf_text_name("/a102"))
0xA3 => Some(pdf_text_name("/a103"))
0xA4 => Some(pdf_text_name("/a104"))
0xA5 => Some(pdf_text_name("/a106"))
0xA6 => Some(pdf_text_name("/a107"))
0xA7 => Some(pdf_text_name("/a108"))
0xA8 => Some(pdf_text_name("/a112"))
0xA9 => Some(pdf_text_name("/a111"))
0xAA => Some(pdf_text_name("/a110"))
0xAB => Some(pdf_text_name("/a109"))
0xAC => Some(pdf_text_name("/a120"))
0xAD => Some(pdf_text_name("/a121"))
0xAE => Some(pdf_text_name("/a122"))
0xAF => Some(pdf_text_name("/a123"))
0xB0 => Some(pdf_text_name("/a124"))
0xB1 => Some(pdf_text_name("/a125"))
0xB2 => Some(pdf_text_name("/a126"))
0xB3 => Some(pdf_text_name("/a127"))
0xB4 => Some(pdf_text_name("/a128"))
0xB5 => Some(pdf_text_name("/a129"))
0xB6 => Some(pdf_text_name("/a130"))
0xB7 => Some(pdf_text_name("/a131"))
0xB8 => Some(pdf_text_name("/a132"))
0xB9 => Some(pdf_text_name("/a133"))
0xBA => Some(pdf_text_name("/a134"))
0xBB => Some(pdf_text_name("/a135"))
0xBC => Some(pdf_text_name("/a136"))
0xBD => Some(pdf_text_name("/a137"))
0xBE => Some(pdf_text_name("/a138"))
0xBF => Some(pdf_text_name("/a139"))
0xC0 => Some(pdf_text_name("/a140"))
0xC1 => Some(pdf_text_name("/a141"))
0xC2 => Some(pdf_text_name("/a142"))
0xC3 => Some(pdf_text_name("/a143"))
0xC4 => Some(pdf_text_name("/a144"))
0xC5 => Some(pdf_text_name("/a145"))
0xC6 => Some(pdf_text_name("/a146"))
0xC7 => Some(pdf_text_name("/a147"))
0xC8 => Some(pdf_text_name("/a148"))
0xC9 => Some(pdf_text_name("/a149"))
0xCA => Some(pdf_text_name("/a150"))
0xCB => Some(pdf_text_name("/a151"))
0xCC => Some(pdf_text_name("/a152"))
0xCD => Some(pdf_text_name("/a153"))
0xCE => Some(pdf_text_name("/a154"))
0xCF => Some(pdf_text_name("/a155"))
0xD0 => Some(pdf_text_name("/a156"))
0xD1 => Some(pdf_text_name("/a157"))
0xD2 => Some(pdf_text_name("/a158"))
0xD3 => Some(pdf_text_name("/a159"))
0xD4 => Some(pdf_text_name("/a160"))
0xD5 => Some(pdf_text_name("/a161"))
0xD6 => Some(pdf_text_name("/a163"))
0xD7 => Some(pdf_text_name("/a164"))
0xD8 => Some(pdf_text_name("/a196"))
0xD9 => Some(pdf_text_name("/a165"))
0xDA => Some(pdf_text_name("/a192"))
0xDB => Some(pdf_text_name("/a166"))
0xDC => Some(pdf_text_name("/a167"))
0xDD => Some(pdf_text_name("/a168"))
0xDE => Some(pdf_text_name("/a169"))
0xDF => Some(pdf_text_name("/a170"))
0xE0 => Some(pdf_text_name("/a171"))
0xE1 => Some(pdf_text_name("/a172"))
0xE2 => Some(pdf_text_name("/a173"))
0xE3 => Some(pdf_text_name("/a162"))
0xE4 => Some(pdf_text_name("/a174"))
0xE5 => Some(pdf_text_name("/a175"))
0xE6 => Some(pdf_text_name("/a176"))
0xE7 => Some(pdf_text_name("/a177"))
0xE8 => Some(pdf_text_name("/a178"))
0xE9 => Some(pdf_text_name("/a179"))
0xEA => Some(pdf_text_name("/a193"))
0xEB => Some(pdf_text_name("/a180"))
0xEC => Some(pdf_text_name("/a199"))
0xED => Some(pdf_text_name("/a181"))
0xEE => Some(pdf_text_name("/a200"))
0xEF => Some(pdf_text_name("/a182"))
0xF1 => Some(pdf_text_name("/a201"))
0xF2 => Some(pdf_text_name("/a183"))
0xF3 => Some(pdf_text_name("/a184"))
0xF4 => Some(pdf_text_name("/a197"))
0xF5 => Some(pdf_text_name("/a185"))
0xF6 => Some(pdf_text_name("/a194"))
0xF7 => Some(pdf_text_name("/a198"))
0xF8 => Some(pdf_text_name("/a186"))
0xF9 => Some(pdf_text_name("/a195"))
0xFA => Some(pdf_text_name("/a187"))
0xFB => Some(pdf_text_name("/a188"))
0xFC => Some(pdf_text_name("/a189"))
0xFD => Some(pdf_text_name("/a190"))
0xFE => Some(pdf_text_name("/a191"))
_ => None
}
}
///|
fn pdf_text_difference_glyphname(
differences : ArrayView[PdfEncodingDifference],
code : Int,
) -> PdfName? {
let mut found : PdfName? = None
for difference in differences {
if difference.code == code {
found = Some(difference.name)
}
}
found
}
///|
fn PdfEncoding::pdf_text_glyphname_of_charcode(
self : PdfEncoding,
code : Int,
) -> PdfName? {
match self {
PdfImplicitInFontFile => None
PdfStandardEncoding => pdf_text_standard_glyphname(code)
PdfMacRomanEncoding => pdf_text_macroman_glyphname(code)
PdfWinAnsiEncoding => pdf_text_winansi_glyphname(code)
PdfMacExpertEncoding => pdf_text_macexpert_glyphname(code)
PdfCustomEncoding(base, differences) =>
match pdf_text_difference_glyphname(differences, code) {
Some(name) => Some(name)
None => base.pdf_text_glyphname_of_charcode(code)
}
PdfFillUndefinedWithStandard(base) =>
match base.pdf_text_glyphname_of_charcode(code) {
Some(name) => Some(name)
None => PdfStandardEncoding.pdf_text_glyphname_of_charcode(code)
}
}
}
///|
/// Expand this encoding to a table of defined character-code to glyph-name entries.
///
/// Only codes with a known glyph name are emitted. The table is ordered by
/// increasing one-byte character code.
pub fn PdfEncoding::table(self : PdfEncoding) -> Array[(Int, PdfName)] {
let output : Array[(Int, PdfName)] = []
for code in 0..<256 {
match self.pdf_text_glyphname_of_charcode(code) {
Some(name) => output.push((code, name))
None => ()
}
}
output
}
///|
/// Expand this encoding to glyph-name to character-code entries.
///
/// The order follows `table`; duplicate glyph names are preserved rather than
/// collapsed.
pub fn PdfEncoding::reverse_table(self : PdfEncoding) -> Array[(PdfName, Int)] {
[
for entry in self.table() => (entry.1, entry.0)
]
}
///|
/// Compatibility wrapper for `PdfEncoding::table`.
pub fn pdf_table_of_encoding(encoding : PdfEncoding) -> Array[(Int, PdfName)] {
encoding.table()
}
///|
/// Compatibility wrapper for `PdfEncoding::reverse_table`.
pub fn pdf_reverse_table_of_encoding(
encoding : PdfEncoding,
) -> Array[(PdfName, Int)] {
encoding.reverse_table()
}
///|
fn PdfStandardFontData::pdf_text_glyphname_of_charcode(
self : PdfStandardFontData,
code : Int,
) -> PdfName? {
match self.encoding {
PdfImplicitInFontFile =>
match self.font {
PdfSymbol => pdf_text_symbol_glyphname(code)
PdfZapfDingbats => pdf_text_zapfdingbats_glyphname(code)
_ => PdfStandardEncoding.pdf_text_glyphname_of_charcode(code)
}
_ => self.encoding.pdf_text_glyphname_of_charcode(code)
}
}
///|
fn PdfFont::pdf_text_glyphname_of_charcode(
self : PdfFont,
code : Int,
) -> PdfName? {
match self {
PdfFontStandard(data) => data.pdf_text_glyphname_of_charcode(code)
PdfFontSimple(font) => font.encoding.pdf_text_glyphname_of_charcode(code)
PdfFontCIDKeyed(_) => None
}
}
///|
fn pdf_text_codepoint_of_basic_latin_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/A" => Some(65)
"/B" => Some(66)
"/C" => Some(67)
"/D" => Some(68)
"/E" => Some(69)
"/F" => Some(70)
"/G" => Some(71)
"/H" => Some(72)
"/I" => Some(73)
"/J" => Some(74)
"/K" => Some(75)
"/L" => Some(76)
"/M" => Some(77)
"/N" => Some(78)
"/O" => Some(79)
"/P" => Some(80)
"/Q" => Some(81)
"/R" => Some(82)
"/S" => Some(83)
"/T" => Some(84)
"/U" => Some(85)
"/V" => Some(86)
"/W" => Some(87)
"/X" => Some(88)
"/Y" => Some(89)
"/Z" => Some(90)
"/a" => Some(97)
"/b" => Some(98)
"/c" => Some(99)
"/controlACK" => Some(6)
"/controlBEL" => Some(7)
"/controlBS" => Some(8)
"/controlCAN" => Some(24)
"/controlDC1" => Some(17)
"/controlDC2" => Some(18)
"/controlDC3" => Some(19)
"/controlDC4" => Some(20)
"/controlDEL" => Some(127)
"/controlDLE" => Some(16)
"/controlEM" => Some(25)
"/controlENQ" => Some(5)
"/controlEOT" => Some(4)
"/controlESC" => Some(27)
"/controlETB" => Some(23)
"/controlETX" => Some(3)
"/controlFS" => Some(28)
"/controlGS" => Some(29)
"/controlNAK" => Some(21)
"/controlRS" => Some(30)
"/controlSI" => Some(15)
"/controlSO" => Some(14)
"/controlSOT" => Some(2)
"/controlSTX" => Some(1)
"/controlSUB" => Some(26)
"/controlSYN" => Some(22)
"/controlUS" => Some(31)
"/controlVT" => Some(11)
"/d" => Some(100)
"/e" => Some(101)
"/f" => Some(102)
"/g" => Some(103)
"/h" => Some(104)
"/i" => Some(105)
"/j" => Some(106)
"/k" => Some(107)
"/l" => Some(108)
"/m" => Some(109)
"/n" => Some(110)
"/o" => Some(111)
"/p" => Some(112)
"/q" => Some(113)
"/r" => Some(114)
"/s" => Some(115)
"/spacehackarabic" => Some(32)
"/t" => Some(116)
"/u" => Some(117)
"/v" => Some(118)
"/verticalbar" => Some(124)
"/w" => Some(119)
"/x" => Some(120)
"/y" => Some(121)
"/z" => Some(122)
_ => None
}
}
///|
fn pdf_text_codepoint_of_digit_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/zero" => Some(48)
"/one" => Some(49)
"/two" => Some(50)
"/three" => Some(51)
"/four" => Some(52)
"/five" => Some(53)
"/six" => Some(54)
"/seven" => Some(55)
"/eight" => Some(56)
"/nine" => Some(57)
"/zerooldstyle" => Some(0xF730)
"/oneoldstyle" => Some(0xF731)
"/twooldstyle" => Some(0xF732)
"/threeoldstyle" => Some(0xF733)
"/fouroldstyle" => Some(0xF734)
"/fiveoldstyle" => Some(0xF735)
"/sixoldstyle" => Some(0xF736)
"/sevenoldstyle" => Some(0xF737)
"/eightoldstyle" => Some(0xF738)
"/nineoldstyle" => Some(0xF739)
"/zeroinferior" => Some(0x2080)
"/oneinferior" => Some(0x2081)
"/twoinferior" => Some(0x2082)
"/threeinferior" => Some(0x2083)
"/fourinferior" => Some(0x2084)
"/fiveinferior" => Some(0x2085)
"/sixinferior" => Some(0x2086)
"/seveninferior" => Some(0x2087)
"/eightinferior" => Some(0x2088)
"/nineinferior" => Some(0x2089)
"/zerosuperior" => Some(0x2070)
"/onesuperior" => Some(0x00B9)
"/twosuperior" => Some(0x00B2)
"/threesuperior" => Some(0x00B3)
"/oneeighth" => Some(0x215B)
"/threeeighths" => Some(0x215C)
"/fiveeighths" => Some(0x215D)
"/seveneighths" => Some(0x215E)
"/onethird" => Some(0x2153)
"/twothirds" => Some(0x2154)
"/threequartersemdash" => Some(0xF6DE)
"/foursuperior" => Some(0x2074)
"/fivesuperior" => Some(0x2075)
"/sixsuperior" => Some(0x2076)
"/sevensuperior" => Some(0x2077)
"/eightsuperior" => Some(0x2078)
"/ninesuperior" => Some(0x2079)
_ => None
}
}
///|
fn pdf_text_codepoint_of_punctuation_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/space" => Some(32)
"/blank" => Some(0x2423)
"/controlHT" => Some(9)
"/controlLF" => Some(10)
"/controlFF" => Some(12)
"/controlCR" => Some(13)
"/exclam" => Some(33)
"/quotedbl" => Some(34)
"/numbersign" => Some(35)
"/dollar" => Some(36)
"/percent" => Some(37)
"/ampersand" => Some(38)
"/quotesingle" => Some(39)
"/quoteright" => Some(0x2019)
"/parenleft" => Some(40)
"/parenright" => Some(41)
"/asterisk" => Some(42)
"/plus" => Some(43)
"/comma" => Some(44)
"/hyphen" => Some(45)
"/period" => Some(46)
"/slash" => Some(47)
"/colon" => Some(58)
"/semicolon" => Some(59)
"/less" => Some(60)
"/equal" => Some(61)
"/greater" => Some(62)
"/question" => Some(63)
"/at" => Some(64)
"/bracketleft" => Some(91)
"/backslash" => Some(92)
"/bracketright" => Some(93)
"/asciicircum" => Some(94)
"/underscore" => Some(95)
"/grave" => Some(96)
"/quoteleft" => Some(0x2018)
"/braceleft" => Some(123)
"/bar" => Some(124)
"/braceright" => Some(125)
"/asciitilde" => Some(126)
"/Euro" => Some(0x20AC)
"/exclamdown" => Some(0x00A1)
"/cent" => Some(0x00A2)
"/sterling" => Some(0x00A3)
"/fraction" => Some(0x2044)
"/yen" => Some(0x00A5)
"/section" => Some(0x00A7)
"/currency" => Some(0x00A4)
"/nbspace" => Some(0x00A0)
"/nonbreakingspace" => Some(0x00A0)
"/guillemotleft" => Some(0x00AB)
"/guillemotright" => Some(0x00BB)
"/ff" => Some(0xFB00)
"/fi" => Some(0xFB01)
"/fl" => Some(0xFB02)
"/ffi" => Some(0xFB03)
"/ffl" => Some(0xFB04)
"/periodcentered" => Some(0x00B7)
"/middot" => Some(0x00B7)
"/paragraph" => Some(0x00B6)
"/questiondown" => Some(0x00BF)
"/Agrave" => Some(0x00C0)
"/Aacute" => Some(0x00C1)
"/Acircumflex" => Some(0x00C2)
"/Atilde" => Some(0x00C3)
"/AE" => Some(0x00C6)
"/Egrave" => Some(0x00C8)
"/Ecircumflex" => Some(0x00CA)
"/Edieresis" => Some(0x00CB)
"/Igrave" => Some(0x00CC)
"/Iacute" => Some(0x00CD)
"/Icircumflex" => Some(0x00CE)
"/Idieresis" => Some(0x00CF)
"/Eth" => Some(0x00D0)
"/Ograve" => Some(0x00D2)
"/Oacute" => Some(0x00D3)
"/Ocircumflex" => Some(0x00D4)
"/Otilde" => Some(0x00D5)
"/Oslash" => Some(0x00D8)
"/Ugrave" => Some(0x00D9)
"/Uacute" => Some(0x00DA)
"/Ucircumflex" => Some(0x00DB)
"/Yacute" => Some(0x00DD)
"/Thorn" => Some(0x00DE)
"/germandbls" => Some(0x00DF)
"/ae" => Some(0x00E6)
"/eth" => Some(0x00F0)
"/oslash" => Some(0x00F8)
"/yacute" => Some(0x00FD)
"/thorn" => Some(0x00FE)
"/ydieresis" => Some(0x00FF)
"/Adieresis" => Some(0x00C4)
"/Aring" => Some(0x00C5)
"/Ccedilla" => Some(0x00C7)
"/Eacute" => Some(0x00C9)
"/Ntilde" => Some(0x00D1)
"/Odieresis" => Some(0x00D6)
"/Udieresis" => Some(0x00DC)
"/aacute" => Some(0x00E1)
"/agrave" => Some(0x00E0)
"/acircumflex" => Some(0x00E2)
"/adieresis" => Some(0x00E4)
"/atilde" => Some(0x00E3)
"/aring" => Some(0x00E5)
"/ccedilla" => Some(0x00E7)
"/egrave" => Some(0x00E8)
"/ecircumflex" => Some(0x00EA)
"/edieresis" => Some(0x00EB)
"/brokenbar" => Some(0x00A6)
"/dieresis" => Some(0x00A8)
"/ordfeminine" => Some(0x00AA)
"/logicalnot" => Some(0x00AC)
"/registered" => Some(0x00AE)
"/macron" => Some(0x00AF)
"/overscore" => Some(0x00AF)
"/breve" => Some(0x02D8)
"/dotaccent" => Some(0x02D9)
"/ring" => Some(0x02DA)
"/hungarumlaut" => Some(0x02DD)
"/ogonek" => Some(0x02DB)
"/caron" => Some(0x02C7)
"/dotlessi" => Some(0x0131)
"/Lslash" => Some(0x0141)
"/lslash" => Some(0x0142)
"/degree" => Some(0x00B0)
"/mu1" => Some(0x00B5)
"/twosuperior" => Some(0x00B2)
"/threesuperior" => Some(0x00B3)
"/acute" => Some(0x00B4)
"/cedilla" => Some(0x00B8)
"/onesuperior" => Some(0x00B9)
"/ordmasculine" => Some(0x00BA)
"/onequarter" => Some(0x00BC)
"/onehalf" => Some(0x00BD)
"/threequarters" => Some(0x00BE)
"/iacute" => Some(0x00ED)
"/igrave" => Some(0x00EC)
"/icircumflex" => Some(0x00EE)
"/idieresis" => Some(0x00EF)
"/ntilde" => Some(0x00F1)
"/oacute" => Some(0x00F3)
"/ograve" => Some(0x00F2)
"/ocircumflex" => Some(0x00F4)
"/odieresis" => Some(0x00F6)
"/otilde" => Some(0x00F5)
"/uacute" => Some(0x00FA)
"/ugrave" => Some(0x00F9)
"/ucircumflex" => Some(0x00FB)
"/udieresis" => Some(0x00FC)
"/quotesinglbase" => Some(0x201A)
"/florin" => Some(0x0192)
"/quotedblbase" => Some(0x201E)
"/ellipsis" => Some(0x2026)
"/dagger" => Some(0x2020)
"/daggerdbl" => Some(0x2021)
"/circumflex" => Some(0x02C6)
"/perthousand" => Some(0x2030)
"/Scaron" => Some(0x0160)
"/guilsinglleft" => Some(0x2039)
"/OE" => Some(0x0152)
"/Zcaron" => Some(0x017D)
"/quotedblleft" => Some(0x201C)
"/quotedblright" => Some(0x201D)
"/bullet" => Some(0x2022)
"/endash" => Some(0x2013)
"/emdash" => Some(0x2014)
"/tilde" => Some(0x02DC)
"/trademark" => Some(0x2122)
"/scaron" => Some(0x0161)
"/guilsinglright" => Some(0x203A)
"/oe" => Some(0x0153)
"/zcaron" => Some(0x017E)
"/Ydieresis" => Some(0x0178)
"/copyright" => Some(0x00A9)
"/eacute" => Some(0x00E9)
"/equalsuperior" => Some(0x207C)
"/plussuperior" => Some(0x207A)
"/sfthyphen" => Some(0x00AD)
"/softhyphen" => Some(0x00AD)
"/afii00208" => Some(0x2015)
"/afii299" => Some(0x200E)
"/afii300" => Some(0x200F)
"/afii301" => Some(0x200D)
"/afii61573" => Some(0x202C)
"/afii61574" => Some(0x202D)
"/afii61575" => Some(0x202E)
"/afii61664" => Some(0x200C)
"/asterism" => Some(0x2042)
"/dbllowline" => Some(0x2017)
"/dblverticalbar" => Some(0x2016)
"/enspace" => Some(0x2002)
"/exclamdbl" => Some(0x203C)
"/horizontalbar" => Some(0x2015)
"/hyphentwo" => Some(0x2010)
"/overline" => Some(0x203E)
"/primereversed" => Some(0x2035)
"/quoteleftreversed" => Some(0x201B)
"/quotereversed" => Some(0x201B)
"/referencemark" => Some(0x203B)
"/twodotleader" => Some(0x2025)
"/underscoredbl" => Some(0x2017)
"/zerowidthnonjoiner" => Some(0x200C)
"/zerowidthspace" => Some(0x200B)
_ => None
}
}
///|
fn pdf_text_codepoint_of_ipa_extension_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Gsmallhook" => Some(0x029B)
"/Rsmallinverted" => Some(0x0281)
"/ascript" => Some(0x0251)
"/ascriptturned" => Some(0x0252)
"/aturned" => Some(0x0250)
"/bhook" => Some(0x0253)
"/bilabialclick" => Some(0x0298)
"/ccurl" => Some(0x0255)
"/cstretched" => Some(0x0297)
"/dezh" => Some(0x02A4)
"/dhook" => Some(0x0257)
"/dotlessjstrokehook" => Some(0x0284)
"/dtail" => Some(0x0256)
"/dzaltone" => Some(0x02A3)
"/dzcurl" => Some(0x02A5)
"/eopen" => Some(0x025B)
"/eopenclosed" => Some(0x029A)
"/eopenreversed" => Some(0x025C)
"/eopenreversedclosed" => Some(0x025E)
"/eopenreversedhook" => Some(0x025D)
"/ereversed" => Some(0x0258)
"/esh" => Some(0x0283)
"/eshcurl" => Some(0x0286)
"/eshsquatreversed" => Some(0x0285)
"/ezh" => Some(0x0292)
"/ezhcurl" => Some(0x0293)
"/gammalatinsmall" => Some(0x0263)
"/ghook" => Some(0x0260)
"/glottalstop" => Some(0x0294)
"/glottalstopinverted" => Some(0x0296)
"/glottalstopreversed" => Some(0x0295)
"/glottalstopstroke" => Some(0x02A1)
"/glottalstopstrokereversed" => Some(0x02A2)
"/gscript" => Some(0x0261)
"/henghook" => Some(0x0267)
"/hhook" => Some(0x0266)
"/hturned" => Some(0x0265)
"/iotalatin" => Some(0x0269)
"/istroke" => Some(0x0268)
"/jcrossedtail" => Some(0x029D)
"/jdotlessstroke" => Some(0x025F)
"/kturned" => Some(0x029E)
"/lbelt" => Some(0x026C)
"/lezh" => Some(0x026E)
"/lhookretroflex" => Some(0x026D)
"/lmiddletilde" => Some(0x026B)
"/mhook" => Some(0x0271)
"/mlonglegturned" => Some(0x0270)
"/mturned" => Some(0x026F)
"/nhookleft" => Some(0x0272)
"/nhookretroflex" => Some(0x0273)
"/obarred" => Some(0x0275)
"/omegalatinclosed" => Some(0x0277)
"/oopen" => Some(0x0254)
"/philatin" => Some(0x0278)
"/qhook" => Some(0x02A0)
"/ramshorn" => Some(0x0264)
"/rfishhook" => Some(0x027E)
"/rfishhookreversed" => Some(0x027F)
"/rhook" => Some(0x027D)
"/rhookturned" => Some(0x027B)
"/rlongleg" => Some(0x027C)
"/rlonglegturned" => Some(0x027A)
"/rturned" => Some(0x0279)
"/schwa" => Some(0x0259)
"/schwahook" => Some(0x025A)
"/shook" => Some(0x0282)
"/tccurl" => Some(0x02A8)
"/tesh" => Some(0x02A7)
"/tretroflexhook" => Some(0x0288)
"/ts" => Some(0x02A6)
"/tturned" => Some(0x0287)
"/ubar" => Some(0x0289)
"/upsilonlatin" => Some(0x028A)
"/vhook" => Some(0x028B)
"/vturned" => Some(0x028C)
"/wturned" => Some(0x028D)
"/yturned" => Some(0x028E)
"/zcurl" => Some(0x0291)
"/zretroflexhook" => Some(0x0290)
_ => None
}
}
///|
fn pdf_text_codepoint_of_spacing_modifier_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Rsmallinvertedsuperior" => Some(0x02B6)
"/acutelowmod" => Some(0x02CF)
"/afii57929" => Some(0x02BC)
"/afii64937" => Some(0x02BD)
"/apostrophemod" => Some(0x02BC)
"/arrowheaddownmod" => Some(0x02C5)
"/arrowheadleftmod" => Some(0x02C2)
"/arrowheadrightmod" => Some(0x02C3)
"/arrowheadupmod" => Some(0x02C4)
"/colontriangularhalfmod" => Some(0x02D1)
"/colontriangularmod" => Some(0x02D0)
"/commareversedmod" => Some(0x02BD)
"/commaturnedmod" => Some(0x02BB)
"/dblprimemod" => Some(0x02BA)
"/downtackmod" => Some(0x02D5)
"/firsttonechinese" => Some(0x02C9)
"/fourthtonechinese" => Some(0x02CB)
"/gammasuperior" => Some(0x02E0)
"/glottalstopmod" => Some(0x02C0)
"/glottalstopreversedmod" => Some(0x02C1)
"/glottalstopreversedsuperior" => Some(0x02E4)
"/gravelowmod" => Some(0x02CE)
"/hhooksuperior" => Some(0x02B1)
"/hsuperior" => Some(0x02B0)
"/ilde" => Some(0x02DC)
"/jsuperior" => Some(0x02B2)
"/macronlowmod" => Some(0x02CD)
"/minusmod" => Some(0x02D7)
"/plusmod" => Some(0x02D6)
"/primemod" => Some(0x02B9)
"/rhookturnedsuperior" => Some(0x02B5)
"/rhotichookmod" => Some(0x02DE)
"/ringhalfleft" => Some(0x02BF)
"/ringhalfleftcentered" => Some(0x02D3)
"/ringhalfright" => Some(0x02BE)
"/ringhalfrightcentered" => Some(0x02D2)
"/rturnedsuperior" => Some(0x02B4)
"/secondtonechinese" => Some(0x02CA)
"/tonebarextrahighmod" => Some(0x02E5)
"/tonebarextralowmod" => Some(0x02E9)
"/tonebarhighmod" => Some(0x02E6)
"/tonebarlowmod" => Some(0x02E8)
"/tonebarmidmod" => Some(0x02E7)
"/uptackmod" => Some(0x02D4)
"/verticallinelowmod" => Some(0x02CC)
"/verticallinemod" => Some(0x02C8)
"/wsuperior" => Some(0x02B7)
"/xsuperior" => Some(0x02E3)
"/ysuperior" => Some(0x02B8)
_ => None
}
}
///|
fn pdf_text_codepoint_of_combining_mark_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/acutebelowcmb" => Some(0x0317)
"/acutecmb" => Some(0x0301)
"/acutecomb" => Some(0x0301)
"/acutetonecmb" => Some(0x0341)
"/brevebelowcmb" => Some(0x032E)
"/brevecmb" => Some(0x0306)
"/breveinvertedbelowcmb" => Some(0x032F)
"/breveinvertedcmb" => Some(0x0311)
"/breveinverteddoublecmb" => Some(0x0361)
"/bridgebelowcmb" => Some(0x032A)
"/bridgeinvertedbelowcmb" => Some(0x033A)
"/candrabinducmb" => Some(0x0310)
"/caronbelowcmb" => Some(0x032C)
"/caroncmb" => Some(0x030C)
"/cedillacmb" => Some(0x0327)
"/circumflexbelowcmb" => Some(0x032D)
"/circumflexcmb" => Some(0x0302)
"/commaabovecmb" => Some(0x0313)
"/commaaboverightcmb" => Some(0x0315)
"/commareversedabovecmb" => Some(0x0314)
"/commaturnedabovecmb" => Some(0x0312)
"/dblarchinvertedbelowcmb" => Some(0x032B)
"/dblgravecmb" => Some(0x030F)
"/dbllowlinecmb" => Some(0x0333)
"/dbloverlinecmb" => Some(0x033F)
"/dblverticallineabovecmb" => Some(0x030E)
"/dialytikatonoscmb" => Some(0x0344)
"/dieresisbelowcmb" => Some(0x0324)
"/dieresiscmb" => Some(0x0308)
"/dotaccentcmb" => Some(0x0307)
"/dotbelowcmb" => Some(0x0323)
"/dotbelowcomb" => Some(0x0323)
"/downtackbelowcmb" => Some(0x031E)
"/gravebelowcmb" => Some(0x0316)
"/gravecmb" => Some(0x0300)
"/gravecomb" => Some(0x0300)
"/gravetonecmb" => Some(0x0340)
"/hookabovecomb" => Some(0x0309)
"/hookcmb" => Some(0x0309)
"/hookpalatalizedbelowcmb" => Some(0x0321)
"/hookretroflexbelowcmb" => Some(0x0322)
"/horncmb" => Some(0x031B)
"/hungarumlautcmb" => Some(0x030B)
"/koroniscmb" => Some(0x0343)
"/leftangleabovecmb" => Some(0x031A)
"/lefttackbelowcmb" => Some(0x0318)
"/lowlinecmb" => Some(0x0332)
"/macronbelowcmb" => Some(0x0331)
"/macroncmb" => Some(0x0304)
"/minusbelowcmb" => Some(0x0320)
"/ogonekcmb" => Some(0x0328)
"/overlinecmb" => Some(0x0305)
"/perispomenigreekcmb" => Some(0x0342)
"/plusbelowcmb" => Some(0x031F)
"/righttackbelowcmb" => Some(0x0319)
"/ringbelowcmb" => Some(0x0325)
"/ringcmb" => Some(0x030A)
"/ringhalfleftbelowcmb" => Some(0x031C)
"/ringhalfrightbelowcmb" => Some(0x0339)
"/seagullbelowcmb" => Some(0x033C)
"/soliduslongoverlaycmb" => Some(0x0338)
"/solidusshortoverlaycmb" => Some(0x0337)
"/squarebelowcmb" => Some(0x033B)
"/strokelongoverlaycmb" => Some(0x0336)
"/strokeshortoverlaycmb" => Some(0x0335)
"/tildebelowcmb" => Some(0x0330)
"/tildecmb" => Some(0x0303)
"/tildecomb" => Some(0x0303)
"/tildedoublecmb" => Some(0x0360)
"/tildeoverlaycmb" => Some(0x0334)
"/tildeverticalcmb" => Some(0x033E)
"/uptackbelowcmb" => Some(0x031D)
"/verticallineabovecmb" => Some(0x030D)
"/verticallinebelowcmb" => Some(0x0329)
"/xabovecmb" => Some(0x033D)
"/ypogegrammenigreekcmb" => Some(0x0345)
_ => None
}
}
///|
fn pdf_text_codepoint_of_currency_letterlike_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/afii08941" => Some(0x20A4)
"/afii57636" => Some(0x20AA)
"/colonsign" => Some(0x20A1)
"/cruzeiro" => Some(0x20A2)
"/dong" => Some(0x20AB)
"/euro" => Some(0x20AC)
"/franc" => Some(0x20A3)
"/lira" => Some(0x20A4)
"/newsheqelsign" => Some(0x20AA)
"/peseta" => Some(0x20A7)
"/sheqel" => Some(0x20AA)
"/sheqelhebrew" => Some(0x20AA)
"/won" => Some(0x20A9)
"/Ohm" => Some(0x2126)
"/afii61248" => Some(0x2105)
"/afii61289" => Some(0x2113)
"/afii61352" => Some(0x2116)
"/angstrom" => Some(0x212B)
"/careof" => Some(0x2105)
"/centigrade" => Some(0x2103)
"/estimated" => Some(0x212E)
"/fahrenheit" => Some(0x2109)
"/lsquare" => Some(0x2113)
"/numero" => Some(0x2116)
"/prescription" => Some(0x211E)
"/telephone" => Some(0x2121)
_ => None
}
}
///|
fn pdf_text_codepoint_of_arrow_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/arrowdashdown" => Some(0x21E3)
"/arrowdashleft" => Some(0x21E0)
"/arrowdashright" => Some(0x21E2)
"/arrowdashup" => Some(0x21E1)
"/arrowdownleft" => Some(0x2199)
"/arrowdownright" => Some(0x2198)
"/arrowdownwhite" => Some(0x21E9)
"/arrowleftdbl" => Some(0x21D0)
"/arrowleftdblstroke" => Some(0x21CD)
"/arrowleftoverright" => Some(0x21C6)
"/arrowleftwhite" => Some(0x21E6)
"/arrowrightdblstroke" => Some(0x21CF)
"/arrowrightoverleft" => Some(0x21C4)
"/arrowrightwhite" => Some(0x21E8)
"/arrowtableft" => Some(0x21E4)
"/arrowtabright" => Some(0x21E5)
"/arrowupdn" => Some(0x2195)
"/arrowupdnbse" => Some(0x21A8)
"/arrowupdownbase" => Some(0x21A8)
"/arrowupleft" => Some(0x2196)
"/arrowupleftofdown" => Some(0x21C5)
"/arrowupright" => Some(0x2197)
"/arrowupwhite" => Some(0x21E7)
"/capslock" => Some(0x21EA)
"/dblarrowleft" => Some(0x21D4)
"/dblarrowright" => Some(0x21D2)
"/harpoonleftbarbup" => Some(0x21BC)
"/harpoonrightbarbup" => Some(0x21C0)
"/pagedown" => Some(0x21DF)
"/pageup" => Some(0x21DE)
_ => None
}
}
///|
fn pdf_text_codepoint_of_greek_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Alphatonos" => Some(0x0386)
"/Deicoptic" => Some(0x03EE)
"/Deltagreek" => Some(0x0394)
"/Digammagreek" => Some(0x03DC)
"/Epsilontonos" => Some(0x0388)
"/Etatonos" => Some(0x0389)
"/Feicoptic" => Some(0x03E4)
"/Gangiacoptic" => Some(0x03EA)
"/Horicoptic" => Some(0x03E8)
"/Iotadieresis" => Some(0x03AA)
"/Iotatonos" => Some(0x038A)
"/Kheicoptic" => Some(0x03E6)
"/Koppagreek" => Some(0x03DE)
"/Omegagreek" => Some(0x03A9)
"/Omegatonos" => Some(0x038F)
"/Omicrontonos" => Some(0x038C)
"/Sampigreek" => Some(0x03E0)
"/Sheicoptic" => Some(0x03E2)
"/Shimacoptic" => Some(0x03EC)
"/Stigmagreek" => Some(0x03DA)
"/Upsilonacutehooksymbolgreek" => Some(0x03D3)
"/Upsilondieresis" => Some(0x03AB)
"/Upsilondieresishooksymbolgreek" => Some(0x03D4)
"/Upsilonhooksymbol" => Some(0x03D2)
"/Upsilontonos" => Some(0x038E)
"/alphatonos" => Some(0x03AC)
"/anoteleia" => Some(0x0387)
"/betasymbolgreek" => Some(0x03D0)
"/deicoptic" => Some(0x03EF)
"/dialytikatonos" => Some(0x0385)
"/dieresistonos" => Some(0x0385)
"/epsilontonos" => Some(0x03AD)
"/etatonos" => Some(0x03AE)
"/feicoptic" => Some(0x03E5)
"/gangiacoptic" => Some(0x03EB)
"/horicoptic" => Some(0x03E9)
"/iotadieresis" => Some(0x03CA)
"/iotadieresistonos" => Some(0x0390)
"/iotatonos" => Some(0x03AF)
"/kappasymbolgreek" => Some(0x03F0)
"/kheicoptic" => Some(0x03E7)
"/mugreek" => Some(0x03BC)
"/numeralsigngreek" => Some(0x0374)
"/numeralsignlowergreek" => Some(0x0375)
"/omegatonos" => Some(0x03CE)
"/omicrontonos" => Some(0x03CC)
"/phisymbolgreek" => Some(0x03D5)
"/pisymbolgreek" => Some(0x03D6)
"/questiongreek" => Some(0x037E)
"/rhosymbolgreek" => Some(0x03F1)
"/sheicoptic" => Some(0x03E3)
"/shimacoptic" => Some(0x03ED)
"/sigmafinal" => Some(0x03C2)
"/sigmalunatesymbolgreek" => Some(0x03F2)
"/thetasymbolgreek" => Some(0x03D1)
"/tonos" => Some(0x0384)
"/upsilondieresis" => Some(0x03CB)
"/upsilondieresistonos" => Some(0x03B0)
"/upsilontonos" => Some(0x03CD)
"/yotgreek" => Some(0x03F3)
"/ypogegrammeni" => Some(0x037A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_armenian_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Aybarmenian" => Some(0x0531)
"/Benarmenian" => Some(0x0532)
"/Caarmenian" => Some(0x053E)
"/Chaarmenian" => Some(0x0549)
"/Cheharmenian" => Some(0x0543)
"/Coarmenian" => Some(0x0551)
"/Daarmenian" => Some(0x0534)
"/Echarmenian" => Some(0x0535)
"/Eharmenian" => Some(0x0537)
"/Etarmenian" => Some(0x0538)
"/Feharmenian" => Some(0x0556)
"/Ghadarmenian" => Some(0x0542)
"/Gimarmenian" => Some(0x0533)
"/Hoarmenian" => Some(0x0540)
"/Iniarmenian" => Some(0x053B)
"/Jaarmenian" => Some(0x0541)
"/Jheharmenian" => Some(0x054B)
"/Keharmenian" => Some(0x0554)
"/Kenarmenian" => Some(0x053F)
"/Liwnarmenian" => Some(0x053C)
"/Menarmenian" => Some(0x0544)
"/Nowarmenian" => Some(0x0546)
"/Oharmenian" => Some(0x0555)
"/Peharmenian" => Some(0x054A)
"/Piwrarmenian" => Some(0x0553)
"/Raarmenian" => Some(0x054C)
"/Reharmenian" => Some(0x0550)
"/Seharmenian" => Some(0x054D)
"/Shaarmenian" => Some(0x0547)
"/Tiwnarmenian" => Some(0x054F)
"/Toarmenian" => Some(0x0539)
"/Vewarmenian" => Some(0x054E)
"/Voarmenian" => Some(0x0548)
"/Xeharmenian" => Some(0x053D)
"/Yiarmenian" => Some(0x0545)
"/Yiwnarmenian" => Some(0x0552)
"/Zaarmenian" => Some(0x0536)
"/Zhearmenian" => Some(0x053A)
"/abbreviationmarkarmenian" => Some(0x055F)
"/apostrophearmenian" => Some(0x055A)
"/aybarmenian" => Some(0x0561)
"/benarmenian" => Some(0x0562)
"/caarmenian" => Some(0x056E)
"/chaarmenian" => Some(0x0579)
"/cheharmenian" => Some(0x0573)
"/coarmenian" => Some(0x0581)
"/commaarmenian" => Some(0x055D)
"/daarmenian" => Some(0x0564)
"/echarmenian" => Some(0x0565)
"/echyiwnarmenian" => Some(0x0587)
"/eharmenian" => Some(0x0567)
"/emphasismarkarmenian" => Some(0x055B)
"/etarmenian" => Some(0x0568)
"/exclamarmenian" => Some(0x055C)
"/feharmenian" => Some(0x0586)
"/ghadarmenian" => Some(0x0572)
"/gimarmenian" => Some(0x0563)
"/hoarmenian" => Some(0x0570)
"/iniarmenian" => Some(0x056B)
"/jaarmenian" => Some(0x0571)
"/jheharmenian" => Some(0x057B)
"/keharmenian" => Some(0x0584)
"/kenarmenian" => Some(0x056F)
"/liwnarmenian" => Some(0x056C)
"/menarmenian" => Some(0x0574)
"/nowarmenian" => Some(0x0576)
"/oharmenian" => Some(0x0585)
"/peharmenian" => Some(0x057A)
"/periodarmenian" => Some(0x0589)
"/piwrarmenian" => Some(0x0583)
"/questionarmenian" => Some(0x055E)
"/raarmenian" => Some(0x057C)
"/reharmenian" => Some(0x0580)
"/ringhalfleftarmenian" => Some(0x0559)
"/seharmenian" => Some(0x057D)
"/shaarmenian" => Some(0x0577)
"/tiwnarmenian" => Some(0x057F)
"/toarmenian" => Some(0x0569)
"/vewarmenian" => Some(0x057E)
"/voarmenian" => Some(0x0578)
"/xeharmenian" => Some(0x056D)
"/yiarmenian" => Some(0x0575)
"/yiwnarmenian" => Some(0x0582)
"/zaarmenian" => Some(0x0566)
"/zhearmenian" => Some(0x056A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_devanagari_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/aadeva" => Some(0x0906)
"/aavowelsigndeva" => Some(0x093E)
"/abbreviationsigndeva" => Some(0x0970)
"/acutedeva" => Some(0x0954)
"/adeva" => Some(0x0905)
"/aideva" => Some(0x0910)
"/aivowelsigndeva" => Some(0x0948)
"/anudattadeva" => Some(0x0952)
"/anusvaradeva" => Some(0x0902)
"/audeva" => Some(0x0914)
"/auvowelsigndeva" => Some(0x094C)
"/avagrahadeva" => Some(0x093D)
"/badeva" => Some(0x092C)
"/bhadeva" => Some(0x092D)
"/cadeva" => Some(0x091A)
"/candrabindudeva" => Some(0x0901)
"/chadeva" => Some(0x091B)
"/dadeva" => Some(0x0926)
"/danda" => Some(0x0964)
"/dbldanda" => Some(0x0965)
"/ddadeva" => Some(0x0921)
"/dddhadeva" => Some(0x095C)
"/ddhadeva" => Some(0x0922)
"/dhadeva" => Some(0x0927)
"/ecandradeva" => Some(0x090D)
"/ecandravowelsigndeva" => Some(0x0945)
"/edeva" => Some(0x090F)
"/eightdeva" => Some(0x096E)
"/eshortdeva" => Some(0x090E)
"/eshortvowelsigndeva" => Some(0x0946)
"/evowelsigndeva" => Some(0x0947)
"/fadeva" => Some(0x095E)
"/fivedeva" => Some(0x096B)
"/fourdeva" => Some(0x096A)
"/gadeva" => Some(0x0917)
"/ghadeva" => Some(0x0918)
"/ghhadeva" => Some(0x095A)
"/gravedeva" => Some(0x0953)
"/hadeva" => Some(0x0939)
"/ideva" => Some(0x0907)
"/iideva" => Some(0x0908)
"/iivowelsigndeva" => Some(0x0940)
"/ivowelsigndeva" => Some(0x093F)
"/jadeva" => Some(0x091C)
"/jhadeva" => Some(0x091D)
"/kadeva" => Some(0x0915)
"/khadeva" => Some(0x0916)
"/khhadeva" => Some(0x0959)
"/ladeva" => Some(0x0932)
"/lladeva" => Some(0x0933)
"/llladeva" => Some(0x0934)
"/llvocalicdeva" => Some(0x0961)
"/llvocalicvowelsigndeva" => Some(0x0963)
"/lvocalicdeva" => Some(0x090C)
"/lvocalicvowelsigndeva" => Some(0x0962)
"/madeva" => Some(0x092E)
"/nadeva" => Some(0x0928)
"/ngadeva" => Some(0x0919)
"/ninedeva" => Some(0x096F)
"/nnadeva" => Some(0x0923)
"/nnnadeva" => Some(0x0929)
"/nuktadeva" => Some(0x093C)
"/nyadeva" => Some(0x091E)
"/ocandradeva" => Some(0x0911)
"/ocandravowelsigndeva" => Some(0x0949)
"/odeva" => Some(0x0913)
"/omdeva" => Some(0x0950)
"/onedeva" => Some(0x0967)
"/oshortdeva" => Some(0x0912)
"/oshortvowelsigndeva" => Some(0x094A)
"/ovowelsigndeva" => Some(0x094B)
"/padeva" => Some(0x092A)
"/phadeva" => Some(0x092B)
"/qadeva" => Some(0x0958)
"/radeva" => Some(0x0930)
"/rhadeva" => Some(0x095D)
"/rradeva" => Some(0x0931)
"/rrvocalicdeva" => Some(0x0960)
"/rrvocalicvowelsigndeva" => Some(0x0944)
"/rvocalicdeva" => Some(0x090B)
"/rvocalicvowelsigndeva" => Some(0x0943)
"/sadeva" => Some(0x0938)
"/sevendeva" => Some(0x096D)
"/shadeva" => Some(0x0936)
"/sixdeva" => Some(0x096C)
"/ssadeva" => Some(0x0937)
"/tadeva" => Some(0x0924)
"/thadeva" => Some(0x0925)
"/threedeva" => Some(0x0969)
"/ttadeva" => Some(0x091F)
"/tthadeva" => Some(0x0920)
"/twodeva" => Some(0x0968)
"/udattadeva" => Some(0x0951)
"/udeva" => Some(0x0909)
"/uudeva" => Some(0x090A)
"/uuvowelsigndeva" => Some(0x0942)
"/uvowelsigndeva" => Some(0x0941)
"/vadeva" => Some(0x0935)
"/viramadeva" => Some(0x094D)
"/visargadeva" => Some(0x0903)
"/yadeva" => Some(0x092F)
"/yyadeva" => Some(0x095F)
"/zadeva" => Some(0x095B)
"/zerodeva" => Some(0x0966)
_ => None
}
}
///|
fn pdf_text_codepoint_of_thai_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/angkhankhuthai" => Some(0x0E5A)
"/bahtthai" => Some(0x0E3F)
"/bobaimaithai" => Some(0x0E1A)
"/chochangthai" => Some(0x0E0A)
"/chochanthai" => Some(0x0E08)
"/chochingthai" => Some(0x0E09)
"/chochoethai" => Some(0x0E0C)
"/dochadathai" => Some(0x0E0E)
"/dodekthai" => Some(0x0E14)
"/eightthai" => Some(0x0E58)
"/fivethai" => Some(0x0E55)
"/fofanthai" => Some(0x0E1F)
"/fofathai" => Some(0x0E1D)
"/fongmanthai" => Some(0x0E4F)
"/fourthai" => Some(0x0E54)
"/hohipthai" => Some(0x0E2B)
"/honokhukthai" => Some(0x0E2E)
"/khokhaithai" => Some(0x0E02)
"/khokhonthai" => Some(0x0E05)
"/khokhuatthai" => Some(0x0E03)
"/khokhwaithai" => Some(0x0E04)
"/khomutthai" => Some(0x0E5B)
"/khorakhangthai" => Some(0x0E06)
"/kokaithai" => Some(0x0E01)
"/lakkhangyaothai" => Some(0x0E45)
"/lochulathai" => Some(0x0E2C)
"/lolingthai" => Some(0x0E25)
"/luthai" => Some(0x0E26)
"/maichattawathai" => Some(0x0E4B)
"/maiekthai" => Some(0x0E48)
"/maihanakatthai" => Some(0x0E31)
"/maitaikhuthai" => Some(0x0E47)
"/maithothai" => Some(0x0E49)
"/maitrithai" => Some(0x0E4A)
"/maiyamokthai" => Some(0x0E46)
"/momathai" => Some(0x0E21)
"/ngonguthai" => Some(0x0E07)
"/nikhahitthai" => Some(0x0E4D)
"/ninethai" => Some(0x0E59)
"/nonenthai" => Some(0x0E13)
"/nonuthai" => Some(0x0E19)
"/oangthai" => Some(0x0E2D)
"/onethai" => Some(0x0E51)
"/paiyannoithai" => Some(0x0E2F)
"/phinthuthai" => Some(0x0E3A)
"/phophanthai" => Some(0x0E1E)
"/phophungthai" => Some(0x0E1C)
"/phosamphaothai" => Some(0x0E20)
"/poplathai" => Some(0x0E1B)
"/roruathai" => Some(0x0E23)
"/ruthai" => Some(0x0E24)
"/saraaathai" => Some(0x0E32)
"/saraaethai" => Some(0x0E41)
"/saraaimaimalaithai" => Some(0x0E44)
"/saraaimaimuanthai" => Some(0x0E43)
"/saraamthai" => Some(0x0E33)
"/saraathai" => Some(0x0E30)
"/saraethai" => Some(0x0E40)
"/saraiithai" => Some(0x0E35)
"/saraithai" => Some(0x0E34)
"/saraothai" => Some(0x0E42)
"/saraueethai" => Some(0x0E37)
"/sarauethai" => Some(0x0E36)
"/sarauthai" => Some(0x0E38)
"/sarauuthai" => Some(0x0E39)
"/seventhai" => Some(0x0E57)
"/sixthai" => Some(0x0E56)
"/sorusithai" => Some(0x0E29)
"/sosalathai" => Some(0x0E28)
"/sosothai" => Some(0x0E0B)
"/sosuathai" => Some(0x0E2A)
"/thanthakhatthai" => Some(0x0E4C)
"/thonangmonthothai" => Some(0x0E11)
"/thophuthaothai" => Some(0x0E12)
"/thothahanthai" => Some(0x0E17)
"/thothanthai" => Some(0x0E10)
"/thothongthai" => Some(0x0E18)
"/thothungthai" => Some(0x0E16)
"/threethai" => Some(0x0E53)
"/topatakthai" => Some(0x0E0F)
"/totaothai" => Some(0x0E15)
"/twothai" => Some(0x0E52)
"/wowaenthai" => Some(0x0E27)
"/yamakkanthai" => Some(0x0E4E)
"/yoyakthai" => Some(0x0E22)
"/yoyingthai" => Some(0x0E0D)
"/zerothai" => Some(0x0E50)
_ => None
}
}
///|
fn pdf_text_codepoint_of_math_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/allequal" => Some(0x224C)
"/approaches" => Some(0x2250)
"/approxequalorimage" => Some(0x2252)
"/approximatelyequal" => Some(0x2245)
"/asteriskmath" => Some(0x2217)
"/asymptoticallyequal" => Some(0x2243)
"/because" => Some(0x2235)
"/bulletoperator" => Some(0x2219)
"/circleot" => Some(0x2299)
"/contourintegral" => Some(0x222E)
"/curlyand" => Some(0x22CF)
"/curlyor" => Some(0x22CE)
"/dblintegral" => Some(0x222C)
"/divides" => Some(0x2223)
"/divisionslash" => Some(0x2215)
"/ellipsisvertical" => Some(0x22EE)
"/forall" => Some(0x2200)
"/geometricallyequal" => Some(0x2251)
"/greaterequalorless" => Some(0x22DB)
"/greaterorequivalent" => Some(0x2273)
"/greaterorless" => Some(0x2277)
"/greateroverequal" => Some(0x2267)
"/imageorapproximatelyequal" => Some(0x2253)
"/increment" => Some(0x2206)
"/lessequalorgreater" => Some(0x22DA)
"/lessorequivalent" => Some(0x2272)
"/lessorgreater" => Some(0x2276)
"/lessoverequal" => Some(0x2266)
"/minus" => Some(0x2212)
"/minuscircle" => Some(0x2296)
"/minusplus" => Some(0x2213)
"/muchgreater" => Some(0x226B)
"/muchless" => Some(0x226A)
"/nabla" => Some(0x2207)
"/notcontains" => Some(0x220C)
"/notelementof" => Some(0x2209)
"/notgreater" => Some(0x226F)
"/notgreaternorequal" => Some(0x2271)
"/notgreaternorless" => Some(0x2279)
"/notidentical" => Some(0x2262)
"/notless" => Some(0x226E)
"/notlessnorequal" => Some(0x2270)
"/notparallel" => Some(0x2226)
"/notprecedes" => Some(0x2280)
"/notsucceeds" => Some(0x2281)
"/notsuperset" => Some(0x2285)
"/orthogonal" => Some(0x221F)
"/parallel" => Some(0x2225)
"/pluscircle" => Some(0x2295)
"/precedes" => Some(0x227A)
"/proportion" => Some(0x2237)
"/ratio" => Some(0x2236)
"/reversedtilde" => Some(0x223D)
"/rightangle" => Some(0x221F)
"/righttriangle" => Some(0x22BF)
"/subset" => Some(0x2282)
"/subsetnotequal" => Some(0x228A)
"/subsetorequal" => Some(0x2286)
"/succeeds" => Some(0x227B)
"/superset" => Some(0x2283)
"/supersetnotequal" => Some(0x228B)
"/supersetorequal" => Some(0x2287)
"/tackdown" => Some(0x22A4)
"/tackleft" => Some(0x22A3)
"/thereexists" => Some(0x2203)
"/tildeoperator" => Some(0x223C)
"/timescircle" => Some(0x2297)
_ => None
}
}
///|
fn pdf_text_codepoint_of_number_form_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Oneroman" => Some(0x2160)
"/Tworoman" => Some(0x2161)
"/Threeroman" => Some(0x2162)
"/Fourroman" => Some(0x2163)
"/Fiveroman" => Some(0x2164)
"/Sixroman" => Some(0x2165)
"/Sevenroman" => Some(0x2166)
"/Eightroman" => Some(0x2167)
"/Nineroman" => Some(0x2168)
"/Tenroman" => Some(0x2169)
"/Elevenroman" => Some(0x216A)
"/Twelveroman" => Some(0x216B)
"/oneroman" => Some(0x2170)
"/tworoman" => Some(0x2171)
"/threeroman" => Some(0x2172)
"/fourroman" => Some(0x2173)
"/fiveroman" => Some(0x2174)
"/sixroman" => Some(0x2175)
"/sevenroman" => Some(0x2176)
"/eightroman" => Some(0x2177)
"/nineroman" => Some(0x2178)
"/tenroman" => Some(0x2179)
"/elevenroman" => Some(0x217A)
"/twelveroman" => Some(0x217B)
_ => None
}
}
///|
fn pdf_text_codepoint_of_technical_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/arc" => Some(0x2312)
"/clear" => Some(0x2327)
"/control" => Some(0x2303)
"/deleteleft" => Some(0x232B)
"/deleteright" => Some(0x2326)
"/house" => Some(0x2302)
"/integralbottom" => Some(0x2321)
"/integraltop" => Some(0x2320)
"/logicalnotreversed" => Some(0x2310)
"/option" => Some(0x2325)
"/projective" => Some(0x2305)
"/propellor" => Some(0x2318)
"/revlogicalnot" => Some(0x2310)
_ => None
}
}
///|
fn pdf_text_codepoint_of_enclosed_alnum_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Acircle" => Some(0x24B6)
"/Bcircle" => Some(0x24B7)
"/Ccircle" => Some(0x24B8)
"/Dcircle" => Some(0x24B9)
"/Ecircle" => Some(0x24BA)
"/Fcircle" => Some(0x24BB)
"/Gcircle" => Some(0x24BC)
"/Hcircle" => Some(0x24BD)
"/Icircle" => Some(0x24BE)
"/Jcircle" => Some(0x24BF)
"/Kcircle" => Some(0x24C0)
"/Lcircle" => Some(0x24C1)
"/Mcircle" => Some(0x24C2)
"/Ncircle" => Some(0x24C3)
"/Ocircle" => Some(0x24C4)
"/Pcircle" => Some(0x24C5)
"/Qcircle" => Some(0x24C6)
"/Rcircle" => Some(0x24C7)
"/Scircle" => Some(0x24C8)
"/Tcircle" => Some(0x24C9)
"/Ucircle" => Some(0x24CA)
"/Vcircle" => Some(0x24CB)
"/Wcircle" => Some(0x24CC)
"/Xcircle" => Some(0x24CD)
"/Ycircle" => Some(0x24CE)
"/Zcircle" => Some(0x24CF)
"/acircle" => Some(0x24D0)
"/aparen" => Some(0x249C)
"/bcircle" => Some(0x24D1)
"/bparen" => Some(0x249D)
"/ccircle" => Some(0x24D2)
"/cparen" => Some(0x249E)
"/dcircle" => Some(0x24D3)
"/dparen" => Some(0x249F)
"/ecircle" => Some(0x24D4)
"/eightcircle" => Some(0x2467)
"/eighteencircle" => Some(0x2471)
"/eighteenparen" => Some(0x2485)
"/eighteenperiod" => Some(0x2499)
"/eightparen" => Some(0x247B)
"/eightperiod" => Some(0x248F)
"/elevencircle" => Some(0x246A)
"/elevenparen" => Some(0x247E)
"/elevenperiod" => Some(0x2492)
"/eparen" => Some(0x24A0)
"/fcircle" => Some(0x24D5)
"/fifteencircle" => Some(0x246E)
"/fifteenparen" => Some(0x2482)
"/fifteenperiod" => Some(0x2496)
"/fivecircle" => Some(0x2464)
"/fiveparen" => Some(0x2478)
"/fiveperiod" => Some(0x248C)
"/fourcircle" => Some(0x2463)
"/fourparen" => Some(0x2477)
"/fourperiod" => Some(0x248B)
"/fourteencircle" => Some(0x246D)
"/fourteenparen" => Some(0x2481)
"/fourteenperiod" => Some(0x2495)
"/fparen" => Some(0x24A1)
"/gcircle" => Some(0x24D6)
"/gparen" => Some(0x24A2)
"/hcircle" => Some(0x24D7)
"/hparen" => Some(0x24A3)
"/icircle" => Some(0x24D8)
"/iparen" => Some(0x24A4)
"/jcircle" => Some(0x24D9)
"/jparen" => Some(0x24A5)
"/kcircle" => Some(0x24DA)
"/kparen" => Some(0x24A6)
"/lcircle" => Some(0x24DB)
"/lparen" => Some(0x24A7)
"/mcircle" => Some(0x24DC)
"/mparen" => Some(0x24A8)
"/ncircle" => Some(0x24DD)
"/ninecircle" => Some(0x2468)
"/nineparen" => Some(0x247C)
"/nineperiod" => Some(0x2490)
"/nineteencircle" => Some(0x2472)
"/nineteenparen" => Some(0x2486)
"/nineteenperiod" => Some(0x249A)
"/nparen" => Some(0x24A9)
"/ocircle" => Some(0x24DE)
"/onecircle" => Some(0x2460)
"/oneparen" => Some(0x2474)
"/oneperiod" => Some(0x2488)
"/oparen" => Some(0x24AA)
"/pcircle" => Some(0x24DF)
"/pparen" => Some(0x24AB)
"/qcircle" => Some(0x24E0)
"/qparen" => Some(0x24AC)
"/rcircle" => Some(0x24E1)
"/rparen" => Some(0x24AD)
"/scircle" => Some(0x24E2)
"/sevencircle" => Some(0x2466)
"/sevenparen" => Some(0x247A)
"/sevenperiod" => Some(0x248E)
"/seventeencircle" => Some(0x2470)
"/seventeenparen" => Some(0x2484)
"/seventeenperiod" => Some(0x2498)
"/sixcircle" => Some(0x2465)
"/sixparen" => Some(0x2479)
"/sixperiod" => Some(0x248D)
"/sixteencircle" => Some(0x246F)
"/sixteenparen" => Some(0x2483)
"/sixteenperiod" => Some(0x2497)
"/sparen" => Some(0x24AE)
"/tcircle" => Some(0x24E3)
"/tencircle" => Some(0x2469)
"/tenparen" => Some(0x247D)
"/tenperiod" => Some(0x2491)
"/thirteencircle" => Some(0x246C)
"/thirteenparen" => Some(0x2480)
"/thirteenperiod" => Some(0x2494)
"/threecircle" => Some(0x2462)
"/threeparen" => Some(0x2476)
"/threeperiod" => Some(0x248A)
"/tparen" => Some(0x24AF)
"/twelvecircle" => Some(0x246B)
"/twelveparen" => Some(0x247F)
"/twelveperiod" => Some(0x2493)
"/twentycircle" => Some(0x2473)
"/twentyparen" => Some(0x2487)
"/twentyperiod" => Some(0x249B)
"/twocircle" => Some(0x2461)
"/twoparen" => Some(0x2475)
"/twoperiod" => Some(0x2489)
"/ucircle" => Some(0x24E4)
"/uparen" => Some(0x24B0)
"/vcircle" => Some(0x24E5)
"/vparen" => Some(0x24B1)
"/wcircle" => Some(0x24E6)
"/wparen" => Some(0x24B2)
"/xcircle" => Some(0x24E7)
"/xparen" => Some(0x24B3)
"/ycircle" => Some(0x24E8)
"/yparen" => Some(0x24B4)
"/zcircle" => Some(0x24E9)
"/zparen" => Some(0x24B5)
_ => None
}
}
///|
fn pdf_text_codepoint_of_cjk_symbol_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/anglebracketleft" => Some(0x3008)
"/anglebracketright" => Some(0x3009)
"/blacklenticularbracketleft" => Some(0x3010)
"/blacklenticularbracketright" => Some(0x3011)
"/circlepostalmark" => Some(0x3036)
"/cornerbracketleft" => Some(0x300C)
"/cornerbracketright" => Some(0x300D)
"/dblanglebracketleft" => Some(0x300A)
"/dblanglebracketright" => Some(0x300B)
"/dittomark" => Some(0x3003)
"/eighthangzhou" => Some(0x3028)
"/fivehangzhou" => Some(0x3025)
"/fourhangzhou" => Some(0x3024)
"/getamark" => Some(0x3013)
"/ideographicclose" => Some(0x3006)
"/ideographiccomma" => Some(0x3001)
"/ideographiciterationmark" => Some(0x3005)
"/ideographicperiod" => Some(0x3002)
"/ideographicspace" => Some(0x3000)
"/ideographiczero" => Some(0x3007)
"/jis" => Some(0x3004)
"/ninehangzhou" => Some(0x3029)
"/onehangzhou" => Some(0x3021)
"/postalmark" => Some(0x3012)
"/postalmarkface" => Some(0x3020)
"/quotedblprime" => Some(0x301E)
"/quotedblprimereversed" => Some(0x301D)
"/sevenhangzhou" => Some(0x3027)
"/sixhangzhou" => Some(0x3026)
"/threehangzhou" => Some(0x3023)
"/tortoiseshellbracketleft" => Some(0x3014)
"/tortoiseshellbracketright" => Some(0x3015)
"/twentyhangzhou" => Some(0x5344)
"/twohangzhou" => Some(0x3022)
"/wavedash" => Some(0x301C)
"/whitecornerbracketleft" => Some(0x300E)
"/whitecornerbracketright" => Some(0x300F)
"/whitelenticularbracketleft" => Some(0x3016)
"/whitelenticularbracketright" => Some(0x3017)
"/whitetortoiseshellbracketleft" => Some(0x3018)
"/whitetortoiseshellbracketright" => Some(0x3019)
_ => None
}
}
///|
fn pdf_text_codepoint_of_hiragana_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/ahiragana" => Some(0x3042)
"/asmallhiragana" => Some(0x3041)
"/bahiragana" => Some(0x3070)
"/behiragana" => Some(0x3079)
"/bihiragana" => Some(0x3073)
"/bohiragana" => Some(0x307C)
"/buhiragana" => Some(0x3076)
"/dahiragana" => Some(0x3060)
"/dehiragana" => Some(0x3067)
"/dihiragana" => Some(0x3062)
"/dohiragana" => Some(0x3069)
"/duhiragana" => Some(0x3065)
"/ehiragana" => Some(0x3048)
"/esmallhiragana" => Some(0x3047)
"/gahiragana" => Some(0x304C)
"/gehiragana" => Some(0x3052)
"/gihiragana" => Some(0x304E)
"/gohiragana" => Some(0x3054)
"/guhiragana" => Some(0x3050)
"/hahiragana" => Some(0x306F)
"/hehiragana" => Some(0x3078)
"/hihiragana" => Some(0x3072)
"/hohiragana" => Some(0x307B)
"/huhiragana" => Some(0x3075)
"/ihiragana" => Some(0x3044)
"/ismallhiragana" => Some(0x3043)
"/iterationhiragana" => Some(0x309D)
"/kahiragana" => Some(0x304B)
"/kehiragana" => Some(0x3051)
"/kihiragana" => Some(0x304D)
"/kohiragana" => Some(0x3053)
"/kuhiragana" => Some(0x304F)
"/mahiragana" => Some(0x307E)
"/mehiragana" => Some(0x3081)
"/mihiragana" => Some(0x307F)
"/mohiragana" => Some(0x3082)
"/muhiragana" => Some(0x3080)
"/nahiragana" => Some(0x306A)
"/nehiragana" => Some(0x306D)
"/nhiragana" => Some(0x3093)
"/nihiragana" => Some(0x306B)
"/nohiragana" => Some(0x306E)
"/nuhiragana" => Some(0x306C)
"/ohiragana" => Some(0x304A)
"/osmallhiragana" => Some(0x3049)
"/pahiragana" => Some(0x3071)
"/pehiragana" => Some(0x307A)
"/pihiragana" => Some(0x3074)
"/pohiragana" => Some(0x307D)
"/puhiragana" => Some(0x3077)
"/rahiragana" => Some(0x3089)
"/rehiragana" => Some(0x308C)
"/rihiragana" => Some(0x308A)
"/rohiragana" => Some(0x308D)
"/ruhiragana" => Some(0x308B)
"/sahiragana" => Some(0x3055)
"/sehiragana" => Some(0x305B)
"/semivoicedmarkkana" => Some(0x309C)
"/sihiragana" => Some(0x3057)
"/sohiragana" => Some(0x305D)
"/suhiragana" => Some(0x3059)
"/tahiragana" => Some(0x305F)
"/tehiragana" => Some(0x3066)
"/tihiragana" => Some(0x3061)
"/tohiragana" => Some(0x3068)
"/tuhiragana" => Some(0x3064)
"/tusmallhiragana" => Some(0x3063)
"/uhiragana" => Some(0x3046)
"/usmallhiragana" => Some(0x3045)
"/voicediterationhiragana" => Some(0x309E)
"/voicedmarkkana" => Some(0x309B)
"/vuhiragana" => Some(0x3094)
"/wahiragana" => Some(0x308F)
"/wasmallhiragana" => Some(0x308E)
"/wehiragana" => Some(0x3091)
"/wihiragana" => Some(0x3090)
"/wohiragana" => Some(0x3092)
"/yahiragana" => Some(0x3084)
"/yasmallhiragana" => Some(0x3083)
"/yohiragana" => Some(0x3088)
"/yosmallhiragana" => Some(0x3087)
"/yuhiragana" => Some(0x3086)
"/yusmallhiragana" => Some(0x3085)
"/zahiragana" => Some(0x3056)
"/zehiragana" => Some(0x305C)
"/zihiragana" => Some(0x3058)
"/zohiragana" => Some(0x305E)
"/zuhiragana" => Some(0x305A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_katakana_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/akatakana" => Some(0x30A2)
"/asmallkatakana" => Some(0x30A1)
"/bakatakana" => Some(0x30D0)
"/bekatakana" => Some(0x30D9)
"/bikatakana" => Some(0x30D3)
"/bokatakana" => Some(0x30DC)
"/bukatakana" => Some(0x30D6)
"/dakatakana" => Some(0x30C0)
"/dekatakana" => Some(0x30C7)
"/dikatakana" => Some(0x30C2)
"/dokatakana" => Some(0x30C9)
"/dotkatakana" => Some(0x30FB)
"/dukatakana" => Some(0x30C5)
"/ekatakana" => Some(0x30A8)
"/esmallkatakana" => Some(0x30A7)
"/gakatakana" => Some(0x30AC)
"/gekatakana" => Some(0x30B2)
"/gikatakana" => Some(0x30AE)
"/gokatakana" => Some(0x30B4)
"/gukatakana" => Some(0x30B0)
"/hakatakana" => Some(0x30CF)
"/hekatakana" => Some(0x30D8)
"/hikatakana" => Some(0x30D2)
"/hokatakana" => Some(0x30DB)
"/hukatakana" => Some(0x30D5)
"/ikatakana" => Some(0x30A4)
"/ismallkatakana" => Some(0x30A3)
"/iterationkatakana" => Some(0x30FD)
"/kakatakana" => Some(0x30AB)
"/kasmallkatakana" => Some(0x30F5)
"/kekatakana" => Some(0x30B1)
"/kesmallkatakana" => Some(0x30F6)
"/kikatakana" => Some(0x30AD)
"/kokatakana" => Some(0x30B3)
"/kukatakana" => Some(0x30AF)
"/makatakana" => Some(0x30DE)
"/mekatakana" => Some(0x30E1)
"/mikatakana" => Some(0x30DF)
"/mokatakana" => Some(0x30E2)
"/mukatakana" => Some(0x30E0)
"/nakatakana" => Some(0x30CA)
"/nekatakana" => Some(0x30CD)
"/nikatakana" => Some(0x30CB)
"/nkatakana" => Some(0x30F3)
"/nokatakana" => Some(0x30CE)
"/nukatakana" => Some(0x30CC)
"/okatakana" => Some(0x30AA)
"/osmallkatakana" => Some(0x30A9)
"/pakatakana" => Some(0x30D1)
"/pekatakana" => Some(0x30DA)
"/pikatakana" => Some(0x30D4)
"/pokatakana" => Some(0x30DD)
"/prolongedkana" => Some(0x30FC)
"/pukatakana" => Some(0x30D7)
"/rakatakana" => Some(0x30E9)
"/rekatakana" => Some(0x30EC)
"/rikatakana" => Some(0x30EA)
"/rokatakana" => Some(0x30ED)
"/rukatakana" => Some(0x30EB)
"/sakatakana" => Some(0x30B5)
"/sekatakana" => Some(0x30BB)
"/sikatakana" => Some(0x30B7)
"/sokatakana" => Some(0x30BD)
"/sukatakana" => Some(0x30B9)
"/takatakana" => Some(0x30BF)
"/tekatakana" => Some(0x30C6)
"/tikatakana" => Some(0x30C1)
"/tokatakana" => Some(0x30C8)
"/tukatakana" => Some(0x30C4)
"/tusmallkatakana" => Some(0x30C3)
"/ukatakana" => Some(0x30A6)
"/usmallkatakana" => Some(0x30A5)
"/vakatakana" => Some(0x30F7)
"/vekatakana" => Some(0x30F9)
"/vikatakana" => Some(0x30F8)
"/voicediterationkatakana" => Some(0x30FE)
"/vokatakana" => Some(0x30FA)
"/vukatakana" => Some(0x30F4)
"/wakatakana" => Some(0x30EF)
"/wasmallkatakana" => Some(0x30EE)
"/wekatakana" => Some(0x30F1)
"/wikatakana" => Some(0x30F0)
"/wokatakana" => Some(0x30F2)
"/yakatakana" => Some(0x30E4)
"/yasmallkatakana" => Some(0x30E3)
"/yokatakana" => Some(0x30E8)
"/yosmallkatakana" => Some(0x30E7)
"/yukatakana" => Some(0x30E6)
"/yusmallkatakana" => Some(0x30E5)
"/zakatakana" => Some(0x30B6)
"/zekatakana" => Some(0x30BC)
"/zikatakana" => Some(0x30B8)
"/zokatakana" => Some(0x30BE)
"/zukatakana" => Some(0x30BA)
_ => None
}
}
///|
fn pdf_text_codepoint_of_bopomofo_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/abopomofo" => Some(0x311A)
"/aibopomofo" => Some(0x311E)
"/anbopomofo" => Some(0x3122)
"/angbopomofo" => Some(0x3124)
"/aubopomofo" => Some(0x3120)
"/bbopomofo" => Some(0x3105)
"/cbopomofo" => Some(0x3118)
"/chbopomofo" => Some(0x3114)
"/dbopomofo" => Some(0x3109)
"/ebopomofo" => Some(0x311C)
"/ehbopomofo" => Some(0x311D)
"/eibopomofo" => Some(0x311F)
"/enbopomofo" => Some(0x3123)
"/engbopomofo" => Some(0x3125)
"/erbopomofo" => Some(0x3126)
"/fbopomofo" => Some(0x3108)
"/gbopomofo" => Some(0x310D)
"/hbopomofo" => Some(0x310F)
"/ibopomofo" => Some(0x3127)
"/iubopomofo" => Some(0x3129)
"/jbopomofo" => Some(0x3110)
"/kbopomofo" => Some(0x310E)
"/lbopomofo" => Some(0x310C)
"/mbopomofo" => Some(0x3107)
"/nbopomofo" => Some(0x310B)
"/obopomofo" => Some(0x311B)
"/oubopomofo" => Some(0x3121)
"/pbopomofo" => Some(0x3106)
"/qbopomofo" => Some(0x3111)
"/rbopomofo" => Some(0x3116)
"/sbopomofo" => Some(0x3119)
"/shbopomofo" => Some(0x3115)
"/tbopomofo" => Some(0x310A)
"/ubopomofo" => Some(0x3128)
"/xbopomofo" => Some(0x3112)
"/zbopomofo" => Some(0x3117)
"/zhbopomofo" => Some(0x3113)
_ => None
}
}
///|
fn pdf_text_codepoint_of_box_drawing_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/SF010000" => Some(0x250C)
"/SF020000" => Some(0x2514)
"/SF030000" => Some(0x2510)
"/SF040000" => Some(0x2518)
"/SF050000" => Some(0x253C)
"/SF060000" => Some(0x252C)
"/SF070000" => Some(0x2534)
"/SF080000" => Some(0x251C)
"/SF090000" => Some(0x2524)
"/SF100000" => Some(0x2500)
"/SF110000" => Some(0x2502)
"/SF190000" => Some(0x2561)
"/SF200000" => Some(0x2562)
"/SF210000" => Some(0x2556)
"/SF220000" => Some(0x2555)
"/SF230000" => Some(0x2563)
"/SF240000" => Some(0x2551)
"/SF250000" => Some(0x2557)
"/SF260000" => Some(0x255D)
"/SF270000" => Some(0x255C)
"/SF280000" => Some(0x255B)
"/SF360000" => Some(0x255E)
"/SF370000" => Some(0x255F)
"/SF380000" => Some(0x255A)
"/SF390000" => Some(0x2554)
"/SF400000" => Some(0x2569)
"/SF410000" => Some(0x2566)
"/SF420000" => Some(0x2560)
"/SF430000" => Some(0x2550)
"/SF440000" => Some(0x256C)
"/SF450000" => Some(0x2567)
"/SF460000" => Some(0x2568)
"/SF470000" => Some(0x2564)
"/SF480000" => Some(0x2565)
"/SF490000" => Some(0x2559)
"/SF500000" => Some(0x2558)
"/SF510000" => Some(0x2552)
"/SF520000" => Some(0x2553)
"/SF530000" => Some(0x256B)
"/SF540000" => Some(0x256A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_block_element_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/block" => Some(0x2588)
"/dkshade" => Some(0x2593)
"/dnblock" => Some(0x2584)
"/lfblock" => Some(0x258C)
"/ltshade" => Some(0x2591)
"/rtblock" => Some(0x2590)
"/shade" => Some(0x2592)
"/shadedark" => Some(0x2593)
"/shadelight" => Some(0x2591)
"/shademedium" => Some(0x2592)
"/upblock" => Some(0x2580)
_ => None
}
}
///|
fn pdf_text_codepoint_of_geometric_shape_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/H18533" => Some(0x25CF)
"/H18543" => Some(0x25AA)
"/H18551" => Some(0x25AB)
"/H22073" => Some(0x25A1)
"/blackcircle" => Some(0x25CF)
"/blackdiamond" => Some(0x25C6)
"/blackdownpointingtriangle" => Some(0x25BC)
"/blackleftpointingpointer" => Some(0x25C4)
"/blackleftpointingtriangle" => Some(0x25C0)
"/blacklowerlefttriangle" => Some(0x25E3)
"/blacklowerrighttriangle" => Some(0x25E2)
"/blackrectangle" => Some(0x25AC)
"/blackrightpointingpointer" => Some(0x25BA)
"/blackrightpointingtriangle" => Some(0x25B6)
"/blacksmallsquare" => Some(0x25AA)
"/blacksquare" => Some(0x25A0)
"/blackupperlefttriangle" => Some(0x25E4)
"/blackupperrighttriangle" => Some(0x25E5)
"/blackuppointingsmalltriangle" => Some(0x25B4)
"/blackuppointingtriangle" => Some(0x25B2)
"/bulletinverse" => Some(0x25D8)
"/bullseye" => Some(0x25CE)
"/circle" => Some(0x25CB)
"/circlewithlefthalfblack" => Some(0x25D0)
"/circlewithrighthalfblack" => Some(0x25D1)
"/dottedcircle" => Some(0x25CC)
"/filledbox" => Some(0x25A0)
"/filledrect" => Some(0x25AC)
"/fisheye" => Some(0x25C9)
"/invbullet" => Some(0x25D8)
"/invcircle" => Some(0x25D9)
"/largecircle" => Some(0x25EF)
"/openbullet" => Some(0x25E6)
"/squarediagonalcrosshatchfill" => Some(0x25A9)
"/squarehorizontalfill" => Some(0x25A4)
"/squareorthogonalcrosshatchfill" => Some(0x25A6)
"/squareupperlefttolowerrightfill" => Some(0x25A7)
"/squareupperrighttolowerleftfill" => Some(0x25A8)
"/squareverticalfill" => Some(0x25A5)
"/squarewhitewithsmallblack" => Some(0x25A3)
"/triagdn" => Some(0x25BC)
"/triaglf" => Some(0x25C4)
"/triagrt" => Some(0x25BA)
"/triagup" => Some(0x25B2)
"/whitebullet" => Some(0x25E6)
"/whitecircle" => Some(0x25CB)
"/whitecircleinverse" => Some(0x25D9)
"/whitediamond" => Some(0x25C7)
"/whitediamondcontainingblacksmalldiamond" => Some(0x25C8)
"/whitedownpointingsmalltriangle" => Some(0x25BF)
"/whitedownpointingtriangle" => Some(0x25BD)
"/whiteleftpointingsmalltriangle" => Some(0x25C3)
"/whiteleftpointingtriangle" => Some(0x25C1)
"/whiterightpointingsmalltriangle" => Some(0x25B9)
"/whiterightpointingtriangle" => Some(0x25B7)
"/whitesmallsquare" => Some(0x25AB)
"/whitesquare" => Some(0x25A1)
"/whiteuppointingsmalltriangle" => Some(0x25B5)
"/whiteuppointingtriangle" => Some(0x25B3)
_ => None
}
}
///|
fn pdf_text_codepoint_of_misc_symbol_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/beamedsixteenthnotes" => Some(0x266C)
"/blacksmilingface" => Some(0x263B)
"/blackstar" => Some(0x2605)
"/clubsuitblack" => Some(0x2663)
"/clubsuitwhite" => Some(0x2667)
"/compass" => Some(0x263C)
"/diamondsuitwhite" => Some(0x2662)
"/earth" => Some(0x2641)
"/eighthnotebeamed" => Some(0x266B)
"/female" => Some(0x2640)
"/heartsuitblack" => Some(0x2665)
"/heartsuitwhite" => Some(0x2661)
"/hotsprings" => Some(0x2668)
"/invsmileface" => Some(0x263B)
"/male" => Some(0x2642)
"/mars" => Some(0x2642)
"/musicalnote" => Some(0x266A)
"/musicalnotedbl" => Some(0x266B)
"/musicflatsign" => Some(0x266D)
"/musicsharpsign" => Some(0x266F)
"/pointingindexdownwhite" => Some(0x261F)
"/pointingindexleftwhite" => Some(0x261C)
"/pointingindexrightwhite" => Some(0x261E)
"/pointingindexupwhite" => Some(0x261D)
"/quarternote" => Some(0x2669)
"/smileface" => Some(0x263A)
"/spadesuitblack" => Some(0x2660)
"/spadesuitwhite" => Some(0x2664)
"/sun" => Some(0x263C)
"/telephoneblack" => Some(0x260E)
"/venus" => Some(0x2640)
"/whitesmilingface" => Some(0x263A)
"/whitestar" => Some(0x2606)
"/whitetelephone" => Some(0x260F)
"/yinyang" => Some(0x262F)
_ => None
}
}
///|
fn pdf_text_codepoint_of_latin_extended_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Abreve" => Some(0x0102)
"/Amacron" => Some(0x0100)
"/Aogonek" => Some(0x0104)
"/Cacute" => Some(0x0106)
"/Ccaron" => Some(0x010C)
"/Ccircumflex" => Some(0x0108)
"/Cdot" => Some(0x010A)
"/Cdotaccent" => Some(0x010A)
"/Dcaron" => Some(0x010E)
"/Dcroat" => Some(0x0110)
"/Dslash" => Some(0x0110)
"/Ebreve" => Some(0x0114)
"/Ecaron" => Some(0x011A)
"/Edot" => Some(0x0116)
"/Edotaccent" => Some(0x0116)
"/Emacron" => Some(0x0112)
"/Eng" => Some(0x014A)
"/Eogonek" => Some(0x0118)
"/Gbreve" => Some(0x011E)
"/Gcedilla" => Some(0x0122)
"/Gcircumflex" => Some(0x011C)
"/Gcommaaccent" => Some(0x0122)
"/Gdot" => Some(0x0120)
"/Gdotaccent" => Some(0x0120)
"/Hbar" => Some(0x0126)
"/Hcircumflex" => Some(0x0124)
"/IJ" => Some(0x0132)
"/Ibreve" => Some(0x012C)
"/Idot" => Some(0x0130)
"/Idotaccent" => Some(0x0130)
"/Imacron" => Some(0x012A)
"/Iogonek" => Some(0x012E)
"/Itilde" => Some(0x0128)
"/Jcircumflex" => Some(0x0134)
"/Kcedilla" => Some(0x0136)
"/Kcommaaccent" => Some(0x0136)
"/Lacute" => Some(0x0139)
"/Lcaron" => Some(0x013D)
"/Lcedilla" => Some(0x013B)
"/Lcommaaccent" => Some(0x013B)
"/Ldot" => Some(0x013F)
"/Ldotaccent" => Some(0x013F)
"/Nacute" => Some(0x0143)
"/Ncaron" => Some(0x0147)
"/Ncedilla" => Some(0x0145)
"/Ncommaaccent" => Some(0x0145)
"/Obreve" => Some(0x014E)
"/Odblacute" => Some(0x0150)
"/Ohungarumlaut" => Some(0x0150)
"/Omacron" => Some(0x014C)
"/Racute" => Some(0x0154)
"/Rcaron" => Some(0x0158)
"/Rcedilla" => Some(0x0156)
"/Rcommaaccent" => Some(0x0156)
"/Sacute" => Some(0x015A)
"/Scedilla" => Some(0x015E)
"/Scircumflex" => Some(0x015C)
"/Tbar" => Some(0x0166)
"/Tcaron" => Some(0x0164)
"/Tcedilla" => Some(0x0162)
"/Tcommaaccent" => Some(0x0162)
"/Ubreve" => Some(0x016C)
"/Udblacute" => Some(0x0170)
"/Uhungarumlaut" => Some(0x0170)
"/Umacron" => Some(0x016A)
"/Uogonek" => Some(0x0172)
"/Uring" => Some(0x016E)
"/Utilde" => Some(0x0168)
"/Wcircumflex" => Some(0x0174)
"/Ycircumflex" => Some(0x0176)
"/Zacute" => Some(0x0179)
"/Zdot" => Some(0x017B)
"/Zdotaccent" => Some(0x017B)
"/abreve" => Some(0x0103)
"/amacron" => Some(0x0101)
"/aogonek" => Some(0x0105)
"/cacute" => Some(0x0107)
"/ccaron" => Some(0x010D)
"/ccircumflex" => Some(0x0109)
"/cdot" => Some(0x010B)
"/cdotaccent" => Some(0x010B)
"/dcaron" => Some(0x010F)
"/dcroat" => Some(0x0111)
"/dmacron" => Some(0x0111)
"/ebreve" => Some(0x0115)
"/ecaron" => Some(0x011B)
"/edot" => Some(0x0117)
"/edotaccent" => Some(0x0117)
"/emacron" => Some(0x0113)
"/eng" => Some(0x014B)
"/eogonek" => Some(0x0119)
"/gbreve" => Some(0x011F)
"/gcedilla" => Some(0x0123)
"/gcircumflex" => Some(0x011D)
"/gcommaaccent" => Some(0x0123)
"/gdot" => Some(0x0121)
"/gdotaccent" => Some(0x0121)
"/hbar" => Some(0x0127)
"/hcircumflex" => Some(0x0125)
"/ibreve" => Some(0x012D)
"/ij" => Some(0x0133)
"/imacron" => Some(0x012B)
"/iogonek" => Some(0x012F)
"/itilde" => Some(0x0129)
"/jcircumflex" => Some(0x0135)
"/kcedilla" => Some(0x0137)
"/kcommaaccent" => Some(0x0137)
"/kgreenlandic" => Some(0x0138)
"/lacute" => Some(0x013A)
"/lcaron" => Some(0x013E)
"/lcedilla" => Some(0x013C)
"/lcommaaccent" => Some(0x013C)
"/ldot" => Some(0x0140)
"/ldotaccent" => Some(0x0140)
"/longs" => Some(0x017F)
"/nacute" => Some(0x0144)
"/napostrophe" => Some(0x0149)
"/ncaron" => Some(0x0148)
"/ncedilla" => Some(0x0146)
"/ncommaaccent" => Some(0x0146)
"/obreve" => Some(0x014F)
"/odblacute" => Some(0x0151)
"/ohungarumlaut" => Some(0x0151)
"/omacron" => Some(0x014D)
"/quoterightn" => Some(0x0149)
"/racute" => Some(0x0155)
"/rcaron" => Some(0x0159)
"/rcedilla" => Some(0x0157)
"/rcommaaccent" => Some(0x0157)
"/sacute" => Some(0x015B)
"/scedilla" => Some(0x015F)
"/scircumflex" => Some(0x015D)
"/slong" => Some(0x017F)
"/tbar" => Some(0x0167)
"/tcaron" => Some(0x0165)
"/tcedilla" => Some(0x0163)
"/tcommaaccent" => Some(0x0163)
"/ubreve" => Some(0x016D)
"/udblacute" => Some(0x0171)
"/uhungarumlaut" => Some(0x0171)
"/umacron" => Some(0x016B)
"/uogonek" => Some(0x0173)
"/uring" => Some(0x016F)
"/utilde" => Some(0x0169)
"/wcircumflex" => Some(0x0175)
"/ycircumflex" => Some(0x0177)
"/zacute" => Some(0x017A)
"/zdot" => Some(0x017C)
"/zdotaccent" => Some(0x017C)
"/AEacute" => Some(0x01FC)
"/AEmacron" => Some(0x01E2)
"/Acaron" => Some(0x01CD)
"/Adblgrave" => Some(0x0200)
"/Adieresismacron" => Some(0x01DE)
"/Adotmacron" => Some(0x01E0)
"/Ainvertedbreve" => Some(0x0202)
"/Aringacute" => Some(0x01FA)
"/Bhook" => Some(0x0181)
"/Btopbar" => Some(0x0182)
"/Chook" => Some(0x0187)
"/DZ" => Some(0x01F1)
"/DZcaron" => Some(0x01C4)
"/Dafrican" => Some(0x0189)
"/Dhook" => Some(0x018A)
"/Dtopbar" => Some(0x018B)
"/Dz" => Some(0x01F2)
"/Dzcaron" => Some(0x01C5)
"/Edblgrave" => Some(0x0204)
"/Einvertedbreve" => Some(0x0206)
"/Eopen" => Some(0x0190)
"/Ereversed" => Some(0x018E)
"/Esh" => Some(0x01A9)
"/Ezh" => Some(0x01B7)
"/Ezhcaron" => Some(0x01EE)
"/Ezhreversed" => Some(0x01B8)
"/Fhook" => Some(0x0191)
"/Gacute" => Some(0x01F4)
"/Gammaafrican" => Some(0x0194)
"/Gcaron" => Some(0x01E6)
"/Ghook" => Some(0x0193)
"/Gstroke" => Some(0x01E4)
"/Icaron" => Some(0x01CF)
"/Idblgrave" => Some(0x0208)
"/Iinvertedbreve" => Some(0x020A)
"/Iotaafrican" => Some(0x0196)
"/Istroke" => Some(0x0197)
"/Kcaron" => Some(0x01E8)
"/Khook" => Some(0x0198)
"/LJ" => Some(0x01C7)
"/Lj" => Some(0x01C8)
"/Mturned" => Some(0x019C)
"/NJ" => Some(0x01CA)
"/Nhookleft" => Some(0x019D)
"/Nj" => Some(0x01CB)
"/Ocaron" => Some(0x01D1)
"/Ocenteredtilde" => Some(0x019F)
"/Odblgrave" => Some(0x020C)
"/Ohorn" => Some(0x01A0)
"/Oi" => Some(0x01A2)
"/Oinvertedbreve" => Some(0x020E)
"/Oogonek" => Some(0x01EA)
"/Oogonekmacron" => Some(0x01EC)
"/Oopen" => Some(0x0186)
"/Oslashacute" => Some(0x01FE)
"/Ostrokeacute" => Some(0x01FE)
"/Phook" => Some(0x01A4)
"/Rdblgrave" => Some(0x0210)
"/Rinvertedbreve" => Some(0x0212)
"/Schwa" => Some(0x018F)
"/Scommaaccent" => Some(0x0218)
"/Thook" => Some(0x01AC)
"/Tonefive" => Some(0x01BC)
"/Tonesix" => Some(0x0184)
"/Tonetwo" => Some(0x01A7)
"/Tretroflexhook" => Some(0x01AE)
"/Ucaron" => Some(0x01D3)
"/Udblgrave" => Some(0x0214)
"/Udieresisacute" => Some(0x01D7)
"/Udieresiscaron" => Some(0x01D9)
"/Udieresisgrave" => Some(0x01DB)
"/Udieresismacron" => Some(0x01D5)
"/Uhorn" => Some(0x01AF)
"/Uinvertedbreve" => Some(0x0216)
"/Upsilonafrican" => Some(0x01B1)
"/Vhook" => Some(0x01B2)
"/Yhook" => Some(0x01B3)
"/Zstroke" => Some(0x01B5)
"/acaron" => Some(0x01CE)
"/adblgrave" => Some(0x0201)
"/adieresismacron" => Some(0x01DF)
"/adotmacron" => Some(0x01E1)
"/aeacute" => Some(0x01FD)
"/aemacron" => Some(0x01E3)
"/ainvertedbreve" => Some(0x0203)
"/aringacute" => Some(0x01FB)
"/bstroke" => Some(0x0180)
"/btopbar" => Some(0x0183)
"/chook" => Some(0x0188)
"/clickalveolar" => Some(0x01C2)
"/clickdental" => Some(0x01C0)
"/clicklateral" => Some(0x01C1)
"/clickretroflex" => Some(0x01C3)
"/deltaturned" => Some(0x018D)
"/dtopbar" => Some(0x018C)
"/dz" => Some(0x01F3)
"/dzcaron" => Some(0x01C6)
"/edblgrave" => Some(0x0205)
"/einvertedbreve" => Some(0x0207)
"/eshreversedloop" => Some(0x01AA)
"/eturned" => Some(0x01DD)
"/ezhcaron" => Some(0x01EF)
"/ezhreversed" => Some(0x01B9)
"/ezhtail" => Some(0x01BA)
"/gacute" => Some(0x01F5)
"/gcaron" => Some(0x01E7)
"/glottalinvertedstroke" => Some(0x01BE)
"/gstroke" => Some(0x01E5)
"/hv" => Some(0x0195)
"/icaron" => Some(0x01D0)
"/idblgrave" => Some(0x0209)
"/iinvertedbreve" => Some(0x020B)
"/jcaron" => Some(0x01F0)
"/kcaron" => Some(0x01E9)
"/khook" => Some(0x0199)
"/lambdastroke" => Some(0x019B)
"/lbar" => Some(0x019A)
"/lj" => Some(0x01C9)
"/nj" => Some(0x01CC)
"/nlegrightlong" => Some(0x019E)
"/ocaron" => Some(0x01D2)
"/odblgrave" => Some(0x020D)
"/ohorn" => Some(0x01A1)
"/oi" => Some(0x01A3)
"/oinvertedbreve" => Some(0x020F)
"/oogonek" => Some(0x01EB)
"/oogonekmacron" => Some(0x01ED)
"/oslashacute" => Some(0x01FF)
"/ostrokeacute" => Some(0x01FF)
"/phook" => Some(0x01A5)
"/rdblgrave" => Some(0x0211)
"/rinvertedbreve" => Some(0x0213)
"/scommaaccent" => Some(0x0219)
"/thook" => Some(0x01AD)
"/tonefive" => Some(0x01BD)
"/tonesix" => Some(0x0185)
"/tonetwo" => Some(0x01A8)
"/tpalatalhook" => Some(0x01AB)
"/twostroke" => Some(0x01BB)
"/ucaron" => Some(0x01D4)
"/udblgrave" => Some(0x0215)
"/udieresisacute" => Some(0x01D8)
"/udieresiscaron" => Some(0x01DA)
"/udieresisgrave" => Some(0x01DC)
"/udieresismacron" => Some(0x01D6)
"/uhorn" => Some(0x01B0)
"/uinvertedbreve" => Some(0x0217)
"/wynn" => Some(0x01BF)
"/yhook" => Some(0x01B4)
"/yr" => Some(0x01A6)
"/zstroke" => Some(0x01B6)
_ => None
}
}
///|
fn pdf_text_codepoint_of_hangul_compat_jamo_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/aekorean" => Some(0x3150)
"/akorean" => Some(0x314F)
"/araeaekorean" => Some(0x318E)
"/araeakorean" => Some(0x318D)
"/chieuchkorean" => Some(0x314A)
"/cieuckorean" => Some(0x3148)
"/ekorean" => Some(0x3154)
"/eokorean" => Some(0x3153)
"/eukorean" => Some(0x3161)
"/hangulfiller" => Some(0x3164)
"/hieuhkorean" => Some(0x314E)
"/ieungkorean" => Some(0x3147)
"/ikorean" => Some(0x3163)
"/kapyeounmieumkorean" => Some(0x3171)
"/kapyeounphieuphkorean" => Some(0x3184)
"/kapyeounpieupkorean" => Some(0x3178)
"/kapyeounssangpieupkorean" => Some(0x3179)
"/khieukhkorean" => Some(0x314B)
"/kiyeokkorean" => Some(0x3131)
"/kiyeoksioskorean" => Some(0x3133)
"/mieumkorean" => Some(0x3141)
"/mieumpansioskorean" => Some(0x3170)
"/mieumpieupkorean" => Some(0x316E)
"/mieumsioskorean" => Some(0x316F)
"/nieuncieuckorean" => Some(0x3135)
"/nieunhieuhkorean" => Some(0x3136)
"/nieunkorean" => Some(0x3134)
"/nieunpansioskorean" => Some(0x3168)
"/nieunsioskorean" => Some(0x3167)
"/nieuntikeutkorean" => Some(0x3166)
"/oekorean" => Some(0x315A)
"/okorean" => Some(0x3157)
"/pansioskorean" => Some(0x317F)
"/phieuphkorean" => Some(0x314D)
"/pieupcieuckorean" => Some(0x3176)
"/pieupkiyeokkorean" => Some(0x3172)
"/pieupkorean" => Some(0x3142)
"/pieupsioskiyeokkorean" => Some(0x3174)
"/pieupsioskorean" => Some(0x3144)
"/pieupsiostikeutkorean" => Some(0x3175)
"/pieupthieuthkorean" => Some(0x3177)
"/pieuptikeutkorean" => Some(0x3173)
"/rieulhieuhkorean" => Some(0x3140)
"/rieulkiyeokkorean" => Some(0x313A)
"/rieulkiyeoksioskorean" => Some(0x3169)
"/rieulkorean" => Some(0x3139)
"/rieulmieumkorean" => Some(0x313B)
"/rieulpansioskorean" => Some(0x316C)
"/rieulphieuphkorean" => Some(0x313F)
"/rieulpieupkorean" => Some(0x313C)
"/rieulpieupsioskorean" => Some(0x316B)
"/rieulsioskorean" => Some(0x313D)
"/rieulthieuthkorean" => Some(0x313E)
"/rieultikeutkorean" => Some(0x316A)
"/rieulyeorinhieuhkorean" => Some(0x316D)
"/sioscieuckorean" => Some(0x317E)
"/sioskiyeokkorean" => Some(0x317A)
"/sioskorean" => Some(0x3145)
"/siosnieunkorean" => Some(0x317B)
"/siospieupkorean" => Some(0x317D)
"/siostikeutkorean" => Some(0x317C)
"/ssangcieuckorean" => Some(0x3149)
"/ssanghieuhkorean" => Some(0x3185)
"/ssangieungkorean" => Some(0x3180)
"/ssangkiyeokkorean" => Some(0x3132)
"/ssangnieunkorean" => Some(0x3165)
"/ssangpieupkorean" => Some(0x3143)
"/ssangsioskorean" => Some(0x3146)
"/ssangtikeutkorean" => Some(0x3138)
"/thieuthkorean" => Some(0x314C)
"/tikeutkorean" => Some(0x3137)
"/ukorean" => Some(0x315C)
"/waekorean" => Some(0x3159)
"/wakorean" => Some(0x3158)
"/wekorean" => Some(0x315E)
"/weokorean" => Some(0x315D)
"/wikorean" => Some(0x315F)
"/yaekorean" => Some(0x3152)
"/yakorean" => Some(0x3151)
"/yekorean" => Some(0x3156)
"/yeokorean" => Some(0x3155)
"/yeorinhieuhkorean" => Some(0x3186)
"/yesieungkorean" => Some(0x3181)
"/yesieungpansioskorean" => Some(0x3183)
"/yesieungsioskorean" => Some(0x3182)
"/yikorean" => Some(0x3162)
"/yoikorean" => Some(0x3189)
"/yokorean" => Some(0x315B)
"/yoyaekorean" => Some(0x3188)
"/yoyakorean" => Some(0x3187)
"/yuikorean" => Some(0x318C)
"/yukorean" => Some(0x3160)
"/yuyekorean" => Some(0x318B)
"/yuyeokorean" => Some(0x318A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_enclosed_cjk_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/chieuchacirclekorean" => Some(0x3277)
"/chieuchaparenkorean" => Some(0x3217)
"/chieuchcirclekorean" => Some(0x3269)
"/chieuchparenkorean" => Some(0x3209)
"/cieucacirclekorean" => Some(0x3276)
"/cieucaparenkorean" => Some(0x3216)
"/cieuccirclekorean" => Some(0x3268)
"/cieucparenkorean" => Some(0x3208)
"/cieucuparenkorean" => Some(0x321C)
"/eightideographicparen" => Some(0x3227)
"/fiveideographicparen" => Some(0x3224)
"/fourideographicparen" => Some(0x3223)
"/hieuhacirclekorean" => Some(0x327B)
"/hieuhaparenkorean" => Some(0x321B)
"/hieuhcirclekorean" => Some(0x326D)
"/hieuhparenkorean" => Some(0x320D)
"/ideographearthcircle" => Some(0x328F)
"/ideographfirecircle" => Some(0x328B)
"/ideographicallianceparen" => Some(0x323F)
"/ideographiccallparen" => Some(0x323A)
"/ideographiccentrecircle" => Some(0x32A5)
"/ideographiccongratulationparen" => Some(0x3237)
"/ideographiccorrectcircle" => Some(0x32A3)
"/ideographicearthparen" => Some(0x322F)
"/ideographicenterpriseparen" => Some(0x323D)
"/ideographicexcellentcircle" => Some(0x329D)
"/ideographicfestivalparen" => Some(0x3240)
"/ideographicfinancialcircle" => Some(0x3296)
"/ideographicfinancialparen" => Some(0x3236)
"/ideographicfireparen" => Some(0x322B)
"/ideographichaveparen" => Some(0x3232)
"/ideographichighcircle" => Some(0x32A4)
"/ideographiclaborcircle" => Some(0x3298)
"/ideographiclaborparen" => Some(0x3238)
"/ideographicleftcircle" => Some(0x32A7)
"/ideographiclowcircle" => Some(0x32A6)
"/ideographicmedicinecircle" => Some(0x32A9)
"/ideographicmetalparen" => Some(0x322E)
"/ideographicmoonparen" => Some(0x322A)
"/ideographicnameparen" => Some(0x3234)
"/ideographicprintcircle" => Some(0x329E)
"/ideographicreachparen" => Some(0x3243)
"/ideographicrepresentparen" => Some(0x3239)
"/ideographicresourceparen" => Some(0x323E)
"/ideographicrightcircle" => Some(0x32A8)
"/ideographicsecretcircle" => Some(0x3299)
"/ideographicselfparen" => Some(0x3242)
"/ideographicsocietyparen" => Some(0x3233)
"/ideographicspecialparen" => Some(0x3235)
"/ideographicstockparen" => Some(0x3231)
"/ideographicstudyparen" => Some(0x323B)
"/ideographicsunparen" => Some(0x3230)
"/ideographicsuperviseparen" => Some(0x323C)
"/ideographicwaterparen" => Some(0x322C)
"/ideographicwoodparen" => Some(0x322D)
"/ideographmetalcircle" => Some(0x328E)
"/ideographmooncircle" => Some(0x328A)
"/ideographnamecircle" => Some(0x3294)
"/ideographsuncircle" => Some(0x3290)
"/ideographwatercircle" => Some(0x328C)
"/ideographwoodcircle" => Some(0x328D)
"/ieungacirclekorean" => Some(0x3275)
"/ieungaparenkorean" => Some(0x3215)
"/ieungcirclekorean" => Some(0x3267)
"/ieungparenkorean" => Some(0x3207)
"/khieukhacirclekorean" => Some(0x3278)
"/khieukhaparenkorean" => Some(0x3218)
"/khieukhcirclekorean" => Some(0x326A)
"/khieukhparenkorean" => Some(0x320A)
"/kiyeokacirclekorean" => Some(0x326E)
"/kiyeokaparenkorean" => Some(0x320E)
"/kiyeokcirclekorean" => Some(0x3260)
"/kiyeokparenkorean" => Some(0x3200)
"/koreanstandardsymbol" => Some(0x327F)
"/mieumacirclekorean" => Some(0x3272)
"/mieumaparenkorean" => Some(0x3212)
"/mieumcirclekorean" => Some(0x3264)
"/mieumparenkorean" => Some(0x3204)
"/nieunacirclekorean" => Some(0x326F)
"/nieunaparenkorean" => Some(0x320F)
"/nieuncirclekorean" => Some(0x3261)
"/nieunparenkorean" => Some(0x3201)
"/nineideographicparen" => Some(0x3228)
"/oneideographicparen" => Some(0x3220)
"/phieuphacirclekorean" => Some(0x327A)
"/phieuphaparenkorean" => Some(0x321A)
"/phieuphcirclekorean" => Some(0x326C)
"/phieuphparenkorean" => Some(0x320C)
"/pieupacirclekorean" => Some(0x3273)
"/pieupaparenkorean" => Some(0x3213)
"/pieupcirclekorean" => Some(0x3265)
"/pieupparenkorean" => Some(0x3205)
"/rieulacirclekorean" => Some(0x3271)
"/rieulaparenkorean" => Some(0x3211)
"/rieulcirclekorean" => Some(0x3263)
"/rieulparenkorean" => Some(0x3203)
"/sevenideographicparen" => Some(0x3226)
"/siosacirclekorean" => Some(0x3274)
"/siosaparenkorean" => Some(0x3214)
"/sioscirclekorean" => Some(0x3266)
"/siosparenkorean" => Some(0x3206)
"/sixideographicparen" => Some(0x3225)
"/tenideographicparen" => Some(0x3229)
"/thieuthacirclekorean" => Some(0x3279)
"/thieuthaparenkorean" => Some(0x3219)
"/thieuthcirclekorean" => Some(0x326B)
"/thieuthparenkorean" => Some(0x320B)
"/threeideographicparen" => Some(0x3222)
"/tikeutacirclekorean" => Some(0x3270)
"/tikeutaparenkorean" => Some(0x3210)
"/tikeutcirclekorean" => Some(0x3262)
"/tikeutparenkorean" => Some(0x3202)
"/twoideographicparen" => Some(0x3221)
_ => None
}
}
///|
fn pdf_text_codepoint_of_private_use_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Acute" => Some(0xF6C9)
"/Caron" => Some(0xF6CA)
"/Dieresis" => Some(0xF6CB)
"/DieresisAcute" => Some(0xF6CC)
"/DieresisGrave" => Some(0xF6CD)
"/Grave" => Some(0xF6CE)
"/Hungarumlaut" => Some(0xF6CF)
"/LL" => Some(0xF6BF)
"/Macron" => Some(0xF6D0)
"/afii10063" => Some(0xF6C4)
"/afii10064" => Some(0xF6C5)
"/afii10192" => Some(0xF6C6)
"/afii10831" => Some(0xF6C7)
"/afii10832" => Some(0xF6C8)
"/apple" => Some(0xF8FF)
"/commaaccent" => Some(0xF6C3)
"/cyrBreve" => Some(0xF6D1)
"/cyrFlex" => Some(0xF6D2)
"/cyrbreve" => Some(0xF6D4)
"/cyrflex" => Some(0xF6D5)
"/dblGrave" => Some(0xF6D3)
"/dblgrave" => Some(0xF6D6)
"/dieresisacute" => Some(0xF6D7)
"/dieresisgrave" => Some(0xF6D8)
"/dollarsuperior" => Some(0xF6E4)
"/dotlessj" => Some(0xF6BE)
"/ll" => Some(0xF6C0)
"/maichattawalowleftthai" => Some(0xF895)
"/maichattawalowrightthai" => Some(0xF894)
"/maichattawaupperleftthai" => Some(0xF893)
"/maieklowleftthai" => Some(0xF88C)
"/maieklowrightthai" => Some(0xF88B)
"/maiekupperleftthai" => Some(0xF88A)
"/maihanakatleftthai" => Some(0xF884)
"/maitaikhuleftthai" => Some(0xF889)
"/maitholowleftthai" => Some(0xF88F)
"/maitholowrightthai" => Some(0xF88E)
"/maithoupperleftthai" => Some(0xF88D)
"/maitrilowleftthai" => Some(0xF892)
"/maitrilowrightthai" => Some(0xF891)
"/maitriupperleftthai" => Some(0xF890)
"/nikhahitleftthai" => Some(0xF899)
"/saraiileftthai" => Some(0xF886)
"/saraileftthai" => Some(0xF885)
"/saraueeleftthai" => Some(0xF888)
"/saraueleftthai" => Some(0xF887)
"/thanthakhatlowleftthai" => Some(0xF898)
"/thanthakhatlowrightthai" => Some(0xF897)
"/thanthakhatupperleftthai" => Some(0xF896)
_ => None
}
}
///|
fn pdf_text_codepoint_of_expert_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/AEsmall" => Some(0xF7E6)
"/Aacutesmall" => Some(0xF7E1)
"/Acircumflexsmall" => Some(0xF7E2)
"/Acutesmall" => Some(0xF7B4)
"/Adieresissmall" => Some(0xF7E4)
"/Agravesmall" => Some(0xF7E0)
"/Aringsmall" => Some(0xF7E5)
"/Asmall" => Some(0xF761)
"/Atildesmall" => Some(0xF7E3)
"/Brevesmall" => Some(0xF6F4)
"/Bsmall" => Some(0xF762)
"/Caronsmall" => Some(0xF6F5)
"/Ccedillasmall" => Some(0xF7E7)
"/Cedillasmall" => Some(0xF7B8)
"/Circumflexsmall" => Some(0xF6F6)
"/Csmall" => Some(0xF763)
"/Dieresissmall" => Some(0xF7A8)
"/Dotaccentsmall" => Some(0xF6F7)
"/Dsmall" => Some(0xF764)
"/Eacutesmall" => Some(0xF7E9)
"/Ecircumflexsmall" => Some(0xF7EA)
"/Edieresissmall" => Some(0xF7EB)
"/Egravesmall" => Some(0xF7E8)
"/Esmall" => Some(0xF765)
"/Ethsmall" => Some(0xF7F0)
"/Fsmall" => Some(0xF766)
"/Gravesmall" => Some(0xF760)
"/Gsmall" => Some(0xF767)
"/Hsmall" => Some(0xF768)
"/Hungarumlautsmall" => Some(0xF6F8)
"/Iacutesmall" => Some(0xF7ED)
"/Icircumflexsmall" => Some(0xF7EE)
"/Idieresissmall" => Some(0xF7EF)
"/Igravesmall" => Some(0xF7EC)
"/Ismall" => Some(0xF769)
"/Jsmall" => Some(0xF76A)
"/Ksmall" => Some(0xF76B)
"/Lslashsmall" => Some(0xF6F9)
"/Lsmall" => Some(0xF76C)
"/Macronsmall" => Some(0xF7AF)
"/Msmall" => Some(0xF76D)
"/Nsmall" => Some(0xF76E)
"/Ntildesmall" => Some(0xF7F1)
"/OEsmall" => Some(0xF6FA)
"/Oacutesmall" => Some(0xF7F3)
"/Ocircumflexsmall" => Some(0xF7F4)
"/Odieresissmall" => Some(0xF7F6)
"/Ogoneksmall" => Some(0xF6FB)
"/Ogravesmall" => Some(0xF7F2)
"/Oslashsmall" => Some(0xF7F8)
"/Osmall" => Some(0xF76F)
"/Otildesmall" => Some(0xF7F5)
"/Psmall" => Some(0xF770)
"/Qsmall" => Some(0xF771)
"/Ringsmall" => Some(0xF6FC)
"/Rsmall" => Some(0xF772)
"/Scaronsmall" => Some(0xF6FD)
"/Ssmall" => Some(0xF773)
"/Thornsmall" => Some(0xF7FE)
"/Tildesmall" => Some(0xF6FE)
"/Tsmall" => Some(0xF774)
"/Uacutesmall" => Some(0xF7FA)
"/Ucircumflexsmall" => Some(0xF7FB)
"/Udieresissmall" => Some(0xF7FC)
"/Ugravesmall" => Some(0xF7F9)
"/Usmall" => Some(0xF775)
"/Vsmall" => Some(0xF776)
"/Wsmall" => Some(0xF777)
"/Xsmall" => Some(0xF778)
"/Yacutesmall" => Some(0xF7FD)
"/Ydieresissmall" => Some(0xF7FF)
"/Ysmall" => Some(0xF779)
"/Zcaronsmall" => Some(0xF6FF)
"/Zsmall" => Some(0xF77A)
"/ampersandsmall" => Some(0xF726)
"/asuperior" => Some(0xF6E9)
"/bsuperior" => Some(0xF6EA)
"/centinferior" => Some(0xF6DF)
"/centoldstyle" => Some(0xF7A2)
"/centsuperior" => Some(0xF6E0)
"/colonmonetary" => Some(0x20A1)
"/commainferior" => Some(0xF6E1)
"/commasuperior" => Some(0xF6E2)
"/dollarinferior" => Some(0xF6E3)
"/dollaroldstyle" => Some(0xF724)
"/dsuperior" => Some(0xF6EB)
"/esuperior" => Some(0xF6EC)
"/exclamdownsmall" => Some(0xF7A1)
"/exclamsmall" => Some(0xF721)
"/figuredash" => Some(0x2012)
"/hypheninferior" => Some(0xF6E5)
"/hyphensuperior" => Some(0xF6E6)
"/isuperior" => Some(0xF6ED)
"/lsuperior" => Some(0xF6EE)
"/msuperior" => Some(0xF6EF)
"/nsuperior" => Some(0x207F)
"/onedotenleader" => Some(0x2024)
"/onefitted" => Some(0xF6DC)
"/osuperior" => Some(0xF6F0)
"/parenleftinferior" => Some(0x208D)
"/parenleftsuperior" => Some(0x207D)
"/parenrightinferior" => Some(0x208E)
"/parenrightsuperior" => Some(0x207E)
"/periodinferior" => Some(0xF6E7)
"/periodsuperior" => Some(0xF6E8)
"/questiondownsmall" => Some(0xF7BF)
"/questionsmall" => Some(0xF73F)
"/rsuperior" => Some(0xF6F1)
"/rupiah" => Some(0xF6DD)
"/ssuperior" => Some(0xF6F2)
"/tsuperior" => Some(0xF6F3)
"/twodotenleader" => Some(0x2025)
_ => None
}
}
///|
fn pdf_text_codepoint_of_symbol_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Alpha" => Some(0x0391)
"/Beta" => Some(0x0392)
"/Gamma" => Some(0x0393)
"/Delta" => Some(0x0394)
"/Epsilon" => Some(0x0395)
"/Zeta" => Some(0x0396)
"/Eta" => Some(0x0397)
"/Theta" => Some(0x0398)
"/Iota" => Some(0x0399)
"/Kappa" => Some(0x039A)
"/Lambda" => Some(0x039B)
"/Mu" => Some(0x039C)
"/Nu" => Some(0x039D)
"/Xi" => Some(0x039E)
"/Omicron" => Some(0x039F)
"/Pi" => Some(0x03A0)
"/Rho" => Some(0x03A1)
"/Sigma" => Some(0x03A3)
"/Tau" => Some(0x03A4)
"/Upsilon" => Some(0x03A5)
"/Upsilon1" => Some(0x03D2)
"/Phi" => Some(0x03A6)
"/Chi" => Some(0x03A7)
"/Psi" => Some(0x03A8)
"/Omega" => Some(0x03A9)
"/alpha" => Some(0x03B1)
"/beta" => Some(0x03B2)
"/gamma" => Some(0x03B3)
"/delta" => Some(0x03B4)
"/epsilon" => Some(0x03B5)
"/zeta" => Some(0x03B6)
"/eta" => Some(0x03B7)
"/theta" => Some(0x03B8)
"/theta1" => Some(0x03D1)
"/iota" => Some(0x03B9)
"/kappa" => Some(0x03BA)
"/lambda" => Some(0x03BB)
"/mu" => Some(0x03BC)
"/nu" => Some(0x03BD)
"/xi" => Some(0x03BE)
"/omicron" => Some(0x03BF)
"/pi" => Some(0x03C0)
"/rho" => Some(0x03C1)
"/sigma" => Some(0x03C3)
"/sigma1" => Some(0x03C2)
"/tau" => Some(0x03C4)
"/upsilon" => Some(0x03C5)
"/phi" => Some(0x03C6)
"/phi1" => Some(0x03D5)
"/chi" => Some(0x03C7)
"/psi" => Some(0x03C8)
"/omega" => Some(0x03C9)
"/omega1" => Some(0x03D6)
"/universal" => Some(0x2200)
"/existential" => Some(0x2203)
"/suchthat" => Some(0x220B)
"/congruent" => Some(0x2245)
"/therefore" => Some(0x2234)
"/perpendicular" => Some(0x22A5)
"/similar" => Some(0x223C)
"/aleph" => Some(0x2135)
"/Ifraktur" => Some(0x2111)
"/Rfraktur" => Some(0x211C)
"/weierstrass" => Some(0x2118)
"/circlemultiply" => Some(0x2297)
"/circleplus" => Some(0x2295)
"/emptyset" => Some(0x2205)
"/intersection" => Some(0x2229)
"/union" => Some(0x222A)
"/propersuperset" => Some(0x2283)
"/reflexsuperset" => Some(0x2287)
"/notsubset" => Some(0x2284)
"/propersubset" => Some(0x2282)
"/reflexsubset" => Some(0x2286)
"/element" => Some(0x2208)
"/notelement" => Some(0x2209)
"/angle" => Some(0x2220)
"/gradient" => Some(0x2207)
"/product" => Some(0x220F)
"/dotmath" => Some(0x22C5)
"/logicalnot" => Some(0x00AC)
"/logicaland" => Some(0x2227)
"/logicalor" => Some(0x2228)
"/arrowdblboth" => Some(0x21D4)
"/arrowdblleft" => Some(0x21D0)
"/arrowdblright" => Some(0x21D2)
"/arrowdbldown" => Some(0x21D3)
"/lessequal" => Some(0x2264)
"/infinity" => Some(0x221E)
"/arrowboth" => Some(0x2194)
"/arrowleft" => Some(0x2190)
"/arrowup" => Some(0x2191)
"/arrowright" => Some(0x2192)
"/arrowdown" => Some(0x2193)
"/degree" => Some(0x00B0)
"/minute" => Some(0x2032)
"/plusminus" => Some(0x00B1)
"/second" => Some(0x2033)
"/florin" => Some(0x0192)
"/greaterequal" => Some(0x2265)
"/multiply" => Some(0x00D7)
"/proportional" => Some(0x221D)
"/partialdiff" => Some(0x2202)
"/divide" => Some(0x00F7)
"/notequal" => Some(0x2260)
"/equivalence" => Some(0x2261)
"/approxequal" => Some(0x2248)
"/summation" => Some(0x2211)
"/radical" => Some(0x221A)
"/radicalex" => Some(0xF8E5)
"/arrowvertex" => Some(0xF8E6)
"/arrowhorizex" => Some(0xF8E7)
"/carriagereturn" => Some(0x21B5)
"/arrowdblup" => Some(0x21D1)
"/angleleft" => Some(0x2329)
"/angleright" => Some(0x232A)
"/registerserif" => Some(0xF6DA)
"/copyrightserif" => Some(0xF6D9)
"/trademarkserif" => Some(0xF6DB)
"/registersans" => Some(0xF8E8)
"/copyrightsans" => Some(0xF8E9)
"/trademarksans" => Some(0xF8EA)
"/parenlefttp" => Some(0xF8EB)
"/parenleftex" => Some(0xF8EC)
"/parenleftbt" => Some(0xF8ED)
"/bracketlefttp" => Some(0xF8EE)
"/bracketleftex" => Some(0xF8EF)
"/bracketleftbt" => Some(0xF8F0)
"/bracelefttp" => Some(0xF8F1)
"/braceleftmid" => Some(0xF8F2)
"/braceleftbt" => Some(0xF8F3)
"/braceex" => Some(0xF8F4)
"/integral" => Some(0x222B)
"/integraltp" => Some(0x2320)
"/integralex" => Some(0xF8F5)
"/integralbt" => Some(0x2321)
"/parenrighttp" => Some(0xF8F6)
"/parenrightex" => Some(0xF8F7)
"/parenrightbt" => Some(0xF8F8)
"/bracketrighttp" => Some(0xF8F9)
"/bracketrightex" => Some(0xF8FA)
"/bracketrightbt" => Some(0xF8FB)
"/bracerighttp" => Some(0xF8FC)
"/bracerightmid" => Some(0xF8FD)
"/bracerightbt" => Some(0xF8FE)
"/lozenge" => Some(0x25CA)
"/spade" => Some(0x2660)
"/club" => Some(0x2663)
"/heart" => Some(0x2665)
"/diamond" => Some(0x2666)
_ => None
}
}
///|
fn pdf_text_codepoint_of_half_fullwidth_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Amonospace" => Some(0xFF21)
"/Bmonospace" => Some(0xFF22)
"/Cmonospace" => Some(0xFF23)
"/Dmonospace" => Some(0xFF24)
"/Emonospace" => Some(0xFF25)
"/Fmonospace" => Some(0xFF26)
"/Gmonospace" => Some(0xFF27)
"/Hmonospace" => Some(0xFF28)
"/Imonospace" => Some(0xFF29)
"/Jmonospace" => Some(0xFF2A)
"/Kmonospace" => Some(0xFF2B)
"/Lmonospace" => Some(0xFF2C)
"/Mmonospace" => Some(0xFF2D)
"/Nmonospace" => Some(0xFF2E)
"/Omonospace" => Some(0xFF2F)
"/Pmonospace" => Some(0xFF30)
"/Qmonospace" => Some(0xFF31)
"/Rmonospace" => Some(0xFF32)
"/Smonospace" => Some(0xFF33)
"/Tmonospace" => Some(0xFF34)
"/Umonospace" => Some(0xFF35)
"/Vmonospace" => Some(0xFF36)
"/Wmonospace" => Some(0xFF37)
"/Xmonospace" => Some(0xFF38)
"/Ymonospace" => Some(0xFF39)
"/Zmonospace" => Some(0xFF3A)
"/akatakanahalfwidth" => Some(0xFF71)
"/amonospace" => Some(0xFF41)
"/ampersandmonospace" => Some(0xFF06)
"/asciicircummonospace" => Some(0xFF3E)
"/asciitildemonospace" => Some(0xFF5E)
"/asmallkatakanahalfwidth" => Some(0xFF67)
"/asteriskmonospace" => Some(0xFF0A)
"/atmonospace" => Some(0xFF20)
"/backslashmonospace" => Some(0xFF3C)
"/barmonospace" => Some(0xFF5C)
"/bmonospace" => Some(0xFF42)
"/braceleftmonospace" => Some(0xFF5B)
"/bracerightmonospace" => Some(0xFF5D)
"/bracketleftmonospace" => Some(0xFF3B)
"/bracketrightmonospace" => Some(0xFF3D)
"/centmonospace" => Some(0xFFE0)
"/cmonospace" => Some(0xFF43)
"/colonmonospace" => Some(0xFF1A)
"/commamonospace" => Some(0xFF0C)
"/cornerbracketlefthalfwidth" => Some(0xFF62)
"/cornerbracketrighthalfwidth" => Some(0xFF63)
"/dmonospace" => Some(0xFF44)
"/dollarmonospace" => Some(0xFF04)
"/eightmonospace" => Some(0xFF18)
"/ekatakanahalfwidth" => Some(0xFF74)
"/emonospace" => Some(0xFF45)
"/equalmonospace" => Some(0xFF1D)
"/esmallkatakanahalfwidth" => Some(0xFF6A)
"/exclammonospace" => Some(0xFF01)
"/fivemonospace" => Some(0xFF15)
"/fmonospace" => Some(0xFF46)
"/fourmonospace" => Some(0xFF14)
"/gmonospace" => Some(0xFF47)
"/gravemonospace" => Some(0xFF40)
"/greatermonospace" => Some(0xFF1E)
"/hakatakanahalfwidth" => Some(0xFF8A)
"/hekatakanahalfwidth" => Some(0xFF8D)
"/hikatakanahalfwidth" => Some(0xFF8B)
"/hmonospace" => Some(0xFF48)
"/hokatakanahalfwidth" => Some(0xFF8E)
"/hukatakanahalfwidth" => Some(0xFF8C)
"/hyphenmonospace" => Some(0xFF0D)
"/ideographiccommaleft" => Some(0xFF64)
"/ikatakanahalfwidth" => Some(0xFF72)
"/imonospace" => Some(0xFF49)
"/ismallkatakanahalfwidth" => Some(0xFF68)
"/jmonospace" => Some(0xFF4A)
"/kakatakanahalfwidth" => Some(0xFF76)
"/katahiraprolongmarkhalfwidth" => Some(0xFF70)
"/kekatakanahalfwidth" => Some(0xFF79)
"/kikatakanahalfwidth" => Some(0xFF77)
"/kmonospace" => Some(0xFF4B)
"/kokatakanahalfwidth" => Some(0xFF7A)
"/kukatakanahalfwidth" => Some(0xFF78)
"/lessmonospace" => Some(0xFF1C)
"/lmonospace" => Some(0xFF4C)
"/macronmonospace" => Some(0xFFE3)
"/makatakanahalfwidth" => Some(0xFF8F)
"/mekatakanahalfwidth" => Some(0xFF92)
"/middledotkatakanahalfwidth" => Some(0xFF65)
"/mikatakanahalfwidth" => Some(0xFF90)
"/mmonospace" => Some(0xFF4D)
"/mokatakanahalfwidth" => Some(0xFF93)
"/mukatakanahalfwidth" => Some(0xFF91)
"/nakatakanahalfwidth" => Some(0xFF85)
"/nekatakanahalfwidth" => Some(0xFF88)
"/nikatakanahalfwidth" => Some(0xFF86)
"/ninemonospace" => Some(0xFF19)
"/nkatakanahalfwidth" => Some(0xFF9D)
"/nmonospace" => Some(0xFF4E)
"/nokatakanahalfwidth" => Some(0xFF89)
"/nukatakanahalfwidth" => Some(0xFF87)
"/numbersignmonospace" => Some(0xFF03)
"/okatakanahalfwidth" => Some(0xFF75)
"/omonospace" => Some(0xFF4F)
"/onemonospace" => Some(0xFF11)
"/osmallkatakanahalfwidth" => Some(0xFF6B)
"/parenleftmonospace" => Some(0xFF08)
"/parenrightmonospace" => Some(0xFF09)
"/percentmonospace" => Some(0xFF05)
"/periodhalfwidth" => Some(0xFF61)
"/periodmonospace" => Some(0xFF0E)
"/plusmonospace" => Some(0xFF0B)
"/pmonospace" => Some(0xFF50)
"/qmonospace" => Some(0xFF51)
"/questionmonospace" => Some(0xFF1F)
"/quotedblmonospace" => Some(0xFF02)
"/quotesinglemonospace" => Some(0xFF07)
"/rakatakanahalfwidth" => Some(0xFF97)
"/rekatakanahalfwidth" => Some(0xFF9A)
"/rikatakanahalfwidth" => Some(0xFF98)
"/rmonospace" => Some(0xFF52)
"/rokatakanahalfwidth" => Some(0xFF9B)
"/rukatakanahalfwidth" => Some(0xFF99)
"/sakatakanahalfwidth" => Some(0xFF7B)
"/sekatakanahalfwidth" => Some(0xFF7E)
"/semicolonmonospace" => Some(0xFF1B)
"/semivoicedmarkkanahalfwidth" => Some(0xFF9F)
"/sevenmonospace" => Some(0xFF17)
"/sikatakanahalfwidth" => Some(0xFF7C)
"/sixmonospace" => Some(0xFF16)
"/slashmonospace" => Some(0xFF0F)
"/smonospace" => Some(0xFF53)
"/sokatakanahalfwidth" => Some(0xFF7F)
"/sterlingmonospace" => Some(0xFFE1)
"/sukatakanahalfwidth" => Some(0xFF7D)
"/takatakanahalfwidth" => Some(0xFF80)
"/tekatakanahalfwidth" => Some(0xFF83)
"/threemonospace" => Some(0xFF13)
"/tikatakanahalfwidth" => Some(0xFF81)
"/tmonospace" => Some(0xFF54)
"/tokatakanahalfwidth" => Some(0xFF84)
"/tukatakanahalfwidth" => Some(0xFF82)
"/tusmallkatakanahalfwidth" => Some(0xFF6F)
"/twomonospace" => Some(0xFF12)
"/ukatakanahalfwidth" => Some(0xFF73)
"/umonospace" => Some(0xFF55)
"/underscoremonospace" => Some(0xFF3F)
"/usmallkatakanahalfwidth" => Some(0xFF69)
"/vmonospace" => Some(0xFF56)
"/voicedmarkkanahalfwidth" => Some(0xFF9E)
"/wakatakanahalfwidth" => Some(0xFF9C)
"/wmonospace" => Some(0xFF57)
"/wokatakanahalfwidth" => Some(0xFF66)
"/wonmonospace" => Some(0xFFE6)
"/xmonospace" => Some(0xFF58)
"/yakatakanahalfwidth" => Some(0xFF94)
"/yasmallkatakanahalfwidth" => Some(0xFF6C)
"/yenmonospace" => Some(0xFFE5)
"/ymonospace" => Some(0xFF59)
"/yokatakanahalfwidth" => Some(0xFF96)
"/yosmallkatakanahalfwidth" => Some(0xFF6E)
"/yukatakanahalfwidth" => Some(0xFF95)
"/yusmallkatakanahalfwidth" => Some(0xFF6D)
"/zeromonospace" => Some(0xFF10)
"/zmonospace" => Some(0xFF5A)
_ => None
}
}
///|
fn pdf_text_codepoint_of_dingbat_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/a1" => Some(0x2701)
"/a2" => Some(0x2702)
"/a202" => Some(0x2703)
"/a3" => Some(0x2704)
"/a4" => Some(0x260E)
"/a5" => Some(0x2706)
"/a119" => Some(0x2707)
"/a118" => Some(0x2708)
"/a117" => Some(0x2709)
"/a11" => Some(0x261B)
"/a12" => Some(0x261E)
"/a13" => Some(0x270C)
"/a14" => Some(0x270D)
"/a15" => Some(0x270E)
"/a16" => Some(0x270F)
"/a105" => Some(0x2710)
"/a17" => Some(0x2711)
"/a18" => Some(0x2712)
"/a19" => Some(0x2713)
"/a20" => Some(0x2714)
"/a21" => Some(0x2715)
"/a22" => Some(0x2716)
"/a23" => Some(0x2717)
"/a24" => Some(0x2718)
"/a25" => Some(0x2719)
"/a26" => Some(0x271A)
"/a27" => Some(0x271B)
"/a28" => Some(0x271C)
"/a6" => Some(0x271D)
"/a7" => Some(0x271E)
"/a8" => Some(0x271F)
"/a9" => Some(0x2720)
"/a10" => Some(0x2721)
"/a29" => Some(0x2722)
"/a30" => Some(0x2723)
"/a31" => Some(0x2724)
"/a32" => Some(0x2725)
"/a33" => Some(0x2726)
"/a34" => Some(0x2727)
"/a35" => Some(0x2605)
"/a36" => Some(0x2729)
"/a37" => Some(0x272A)
"/a38" => Some(0x272B)
"/a39" => Some(0x272C)
"/a40" => Some(0x272D)
"/a41" => Some(0x272E)
"/a42" => Some(0x272F)
"/a43" => Some(0x2730)
"/a44" => Some(0x2731)
"/a45" => Some(0x2732)
"/a46" => Some(0x2733)
"/a47" => Some(0x2734)
"/a48" => Some(0x2735)
"/a49" => Some(0x2736)
"/a50" => Some(0x2737)
"/a51" => Some(0x2738)
"/a52" => Some(0x2739)
"/a53" => Some(0x273A)
"/a54" => Some(0x273B)
"/a55" => Some(0x273C)
"/a56" => Some(0x273D)
"/a57" => Some(0x273E)
"/a58" => Some(0x273F)
"/a59" => Some(0x2740)
"/a60" => Some(0x2741)
"/a61" => Some(0x2742)
"/a62" => Some(0x2743)
"/a63" => Some(0x2744)
"/a64" => Some(0x2745)
"/a65" => Some(0x2746)
"/a66" => Some(0x2747)
"/a67" => Some(0x2748)
"/a68" => Some(0x2749)
"/a69" => Some(0x274A)
"/a70" => Some(0x274B)
"/a71" => Some(0x25CF)
"/a72" => Some(0x274D)
"/a73" => Some(0x25A0)
"/a74" => Some(0x274F)
"/a203" => Some(0x2750)
"/a75" => Some(0x2751)
"/a204" => Some(0x2752)
"/a76" => Some(0x25B2)
"/a77" => Some(0x25BC)
"/a78" => Some(0x25C6)
"/a79" => Some(0x2756)
"/a81" => Some(0x25D7)
"/a82" => Some(0x2758)
"/a83" => Some(0x2759)
"/a84" => Some(0x275A)
"/a97" => Some(0x275B)
"/a98" => Some(0x275C)
"/a99" => Some(0x275D)
"/a100" => Some(0x275E)
"/a101" => Some(0x2761)
"/a102" => Some(0x2762)
"/a103" => Some(0x2763)
"/a104" => Some(0x2764)
"/a106" => Some(0x2765)
"/a107" => Some(0x2766)
"/a108" => Some(0x2767)
"/a112" => Some(0x2663)
"/a111" => Some(0x2666)
"/a110" => Some(0x2665)
"/a109" => Some(0x2660)
"/a89" => Some(0x2768)
"/a90" => Some(0x2769)
"/a93" => Some(0x276A)
"/a94" => Some(0x276B)
"/a91" => Some(0x276C)
"/a92" => Some(0x276D)
"/a205" => Some(0x276E)
"/a85" => Some(0x276F)
"/a206" => Some(0x2770)
"/a86" => Some(0x2771)
"/a87" => Some(0x2772)
"/a88" => Some(0x2773)
"/a95" => Some(0x2774)
"/a96" => Some(0x2775)
"/a120" => Some(0x2460)
"/a121" => Some(0x2461)
"/a122" => Some(0x2462)
"/a123" => Some(0x2463)
"/a124" => Some(0x2464)
"/a125" => Some(0x2465)
"/a126" => Some(0x2466)
"/a127" => Some(0x2467)
"/a128" => Some(0x2468)
"/a129" => Some(0x2469)
"/a130" => Some(0x2776)
"/a131" => Some(0x2777)
"/a132" => Some(0x2778)
"/a133" => Some(0x2779)
"/a134" => Some(0x277A)
"/a135" => Some(0x277B)
"/a136" => Some(0x277C)
"/a137" => Some(0x277D)
"/a138" => Some(0x277E)
"/a139" => Some(0x277F)
"/a140" => Some(0x2780)
"/a141" => Some(0x2781)
"/a142" => Some(0x2782)
"/a143" => Some(0x2783)
"/a144" => Some(0x2784)
"/a145" => Some(0x2785)
"/a146" => Some(0x2786)
"/a147" => Some(0x2787)
"/a148" => Some(0x2788)
"/a149" => Some(0x2789)
"/a150" => Some(0x278A)
"/a151" => Some(0x278B)
"/a152" => Some(0x278C)
"/a153" => Some(0x278D)
"/a154" => Some(0x278E)
"/a155" => Some(0x278F)
"/a156" => Some(0x2790)
"/a157" => Some(0x2791)
"/a158" => Some(0x2792)
"/a159" => Some(0x2793)
"/a160" => Some(0x2794)
"/a161" => Some(0x2192)
"/a163" => Some(0x2194)
"/a164" => Some(0x2195)
"/a196" => Some(0x2798)
"/a165" => Some(0x2799)
"/a192" => Some(0x279A)
"/a166" => Some(0x279B)
"/a167" => Some(0x279C)
"/a168" => Some(0x279D)
"/a169" => Some(0x279E)
"/a170" => Some(0x279F)
"/a171" => Some(0x27A0)
"/a172" => Some(0x27A1)
"/a173" => Some(0x27A2)
"/a162" => Some(0x27A3)
"/a174" => Some(0x27A4)
"/a175" => Some(0x27A5)
"/a176" => Some(0x27A6)
"/a177" => Some(0x27A7)
"/a178" => Some(0x27A8)
"/a179" => Some(0x27A9)
"/a193" => Some(0x27AA)
"/a180" => Some(0x27AB)
"/a199" => Some(0x27AC)
"/a181" => Some(0x27AD)
"/a200" => Some(0x27AE)
"/a182" => Some(0x27AF)
"/a201" => Some(0x27B1)
"/a183" => Some(0x27B2)
"/a184" => Some(0x27B3)
"/a197" => Some(0x27B4)
"/a185" => Some(0x27B5)
"/a194" => Some(0x27B6)
"/a198" => Some(0x27B7)
"/a186" => Some(0x27B8)
"/a195" => Some(0x27B9)
"/a187" => Some(0x27BA)
"/a188" => Some(0x27BB)
"/a189" => Some(0x27BC)
"/a190" => Some(0x27BD)
"/a191" => Some(0x27BE)
"/arrowrightheavy" => Some(0x279E)
"/checkmark" => Some(0x2713)
"/onecircleinversesansserif" => Some(0x278A)
"/twocircleinversesansserif" => Some(0x278B)
"/threecircleinversesansserif" => Some(0x278C)
"/fourcircleinversesansserif" => Some(0x278D)
"/fivecircleinversesansserif" => Some(0x278E)
"/sixcircleinversesansserif" => Some(0x278F)
"/sevencircleinversesansserif" => Some(0x2790)
"/eightcircleinversesansserif" => Some(0x2791)
"/ninecircleinversesansserif" => Some(0x2792)
_ => None
}
}
///|
fn pdf_text_glyphname_base_bytes(name : PdfName) -> BytesView {
let bytes = name.bytes()
let mut end = bytes.length()
let mut index = 0
while index < bytes.length() {
if bytes[index].to_int() == 46 {
end = index
break
}
index += 1
}
bytes[:end]
}
///|
fn pdf_text_valid_unicode_scalar(codepoint : Int) -> Bool {
codepoint >= 0 &&
codepoint <= 0x10FFFF &&
!(codepoint >= 0xD800 && codepoint <= 0xDFFF)
}
///|
fn pdf_text_parse_hex_codepoint(
bytes : BytesView,
start : Int,
stop : Int,
) -> Int? {
guard stop > start else { return None }
let mut value = 0
for index in start.. value = value * 16 + digit
None => return None
}
}
if pdf_text_valid_unicode_scalar(value) {
Some(value)
} else {
None
}
}
///|
fn pdf_text_uni_glyphname_codepoints(base : BytesView) -> Array[Int]? {
guard base.length() > 4 &&
base[0].to_int() == 47 &&
base[1].to_int() == 117 &&
base[2].to_int() == 110 &&
base[3].to_int() == 105 &&
(base.length() - 4) % 4 == 0 else {
return None
}
let output : Array[Int] = []
let mut index = 4
while index < base.length() {
match pdf_text_parse_hex_codepoint(base, index, index + 4) {
Some(codepoint) => output.push(codepoint)
None => return None
}
index += 4
}
Some(output)
}
///|
fn pdf_text_u_glyphname_codepoints(base : BytesView) -> Array[Int]? {
guard base.length() >= 6 &&
base.length() <= 8 &&
base[0].to_int() == 47 &&
base[1].to_int() == 117 else {
return None
}
match pdf_text_parse_hex_codepoint(base, 2, base.length()) {
Some(codepoint) => Some([codepoint])
None => None
}
}
///|
fn pdf_text_upper_hex_letter(byte : Byte) -> Bool {
let value = byte.to_int()
value >= 65 && value <= 70
}
///|
fn pdf_text_truetype_control_high_byte(value : Int) -> Bool {
value == 0x8A ||
value == 0x8B ||
value == 0x8C ||
value == 0x9A ||
value == 0x9B ||
value == 0x9C
}
///|
fn pdf_text_truetype_windows_high_byte_table() -> Array[(Int, Int)] {
[
(0x82, 0x201A),
(0x83, 0x0192),
(0x84, 0x201E),
(0x85, 0x2026),
(0x86, 0x2020),
(0x87, 0x2021),
(0x88, 0x02C6),
(0x89, 0x2030),
(0x8A, 0x0160),
(0x8B, 0x2039),
(0x8C, 0x0152),
(0x91, 0x2018),
(0x92, 0x2019),
(0x93, 0x201C),
(0x94, 0x201D),
(0x95, 0x2022),
(0x96, 0x2013),
(0x97, 0x2014),
(0x98, 0x02DC),
(0x99, 0x2122),
(0x9A, 0x0161),
(0x9B, 0x203A),
(0x9C, 0x0153),
(0x9F, 0x0178),
]
}
///|
fn pdf_text_truetype_high_byte_codepoint(value : Int, low_hex : Byte) -> Int? {
if pdf_text_upper_hex_letter(low_hex) &&
pdf_text_truetype_control_high_byte(value) {
Some(value)
} else {
for entry in pdf_text_truetype_windows_high_byte_table() {
if entry.0 == value {
break Some(entry.1)
}
} nobreak {
None
}
}
}
///|
fn pdf_text_truetype_glyphname_codepoints(base : BytesView) -> Array[Int]? {
guard base.length() == 4 && base[0].to_int() == 47 && base[1].to_int() == 71 else {
return None
}
let high = match pdf_text_hex_digit_value(base[2]) {
Some(value) => value
None => return None
}
let low = match pdf_text_hex_digit_value(base[3]) {
Some(value) => value
None => return None
}
let value = high * 16 + low
if base[2].to_int() == 65 && base[3].to_int() == 54 {
Some([0x00B6])
} else if value == 0x6D && pdf_text_upper_hex_letter(base[3]) {
Some([0x002D])
} else if (value >= 0x20 && value <= 0x7E) || (value >= 0xA0 && value <= 0xFF) {
Some([value])
} else {
match pdf_text_truetype_high_byte_codepoint(value, base[3]) {
Some(codepoint) => Some([codepoint])
None => None
}
}
}
///|
fn pdf_text_glyphname_base_name(name : PdfName, base : BytesView) -> PdfName {
if base.length() == name.byte_length() {
name
} else {
pdf_name_of_bytes(base.to_owned())
}
}
///|
fn pdf_text_codepoint_of_agl_base_glyphname(base_name : PdfName) -> Int? {
match pdf_text_codepoint_of_basic_latin_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_digit_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_punctuation_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_ipa_extension_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_spacing_modifier_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_combining_mark_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_currency_letterlike_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_arrow_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_greek_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_cyrillic_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_armenian_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_hebrew_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_arabic_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_devanagari_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_bengali_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_gurmukhi_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_gujarati_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_thai_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_math_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_number_form_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_technical_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_enclosed_alnum_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_cjk_symbol_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_hiragana_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_katakana_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_bopomofo_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_hangul_compat_jamo_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_enclosed_cjk_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_cjk_compat_square_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_presentation_form_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_box_drawing_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_block_element_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_geometric_shape_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_misc_symbol_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_latin_extended_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_latin_ext_additional_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_private_use_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_expert_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_symbol_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
match pdf_text_codepoint_of_half_fullwidth_glyphname(base_name) {
Some(codepoint) => return Some(codepoint)
None => ()
}
pdf_text_codepoint_of_dingbat_glyphname(base_name)
}
///|
fn pdf_text_codepoints_of_glyphname(name : PdfName) -> Array[Int]? {
let base = pdf_text_glyphname_base_bytes(name)
match pdf_text_uni_glyphname_codepoints(base) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_u_glyphname_codepoints(base) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_truetype_glyphname_codepoints(base) {
Some(codepoints) => Some(codepoints)
None =>
if base.length() == 2 && base[0].to_int() == 47 {
let value = base[1].to_int()
if (value >= 65 && value <= 90) || (value >= 97 && value <= 122) {
Some([value])
} else {
None
}
} else {
let base_name = pdf_text_glyphname_base_name(name, base)
match pdf_text_codepoints_of_agl_sequence_glyphname(base_name) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_codepoint_of_agl_base_glyphname(base_name) {
Some(codepoint) => Some([codepoint])
None => None
}
}
}
}
}
}
}
///|
fn pdf_text_codepoint_of_agl_symbol_conflict_glyphname(name : PdfName) -> Int? {
match pdf_text_string_of_name(name) {
"/Delta" => Some(0x2206)
"/Omega" => Some(0x2126)
"/mu" => Some(0x00B5)
_ => None
}
}
///|
fn PdfFont::pdf_text_uses_symbol_codepoints(self : PdfFont) -> Bool {
match self {
PdfFontStandard(data) =>
data.font == PdfSymbol && data.encoding == PdfImplicitInFontFile
_ => false
}
}
///|
fn PdfFont::pdf_text_codepoints_of_glyphname(
self : PdfFont,
glyphname : PdfName,
) -> Array[Int]? {
if self.pdf_text_uses_symbol_codepoints() {
pdf_text_codepoints_of_glyphname(glyphname)
} else {
match pdf_text_codepoint_of_agl_symbol_conflict_glyphname(glyphname) {
Some(codepoint) => Some([codepoint])
None => pdf_text_codepoints_of_glyphname(glyphname)
}
}
}
///|
fn PdfFont::pdf_text_glyphname_has_single_codepoint(
self : PdfFont,
glyphname : PdfName,
codepoint : Int,
) -> Bool {
match self.pdf_text_codepoints_of_glyphname(glyphname) {
Some([single]) if single == codepoint => true
_ => false
}
}
///|
fn PdfEncoding::pdf_text_has_macexpert_base(self : PdfEncoding) -> Bool {
match self {
PdfMacExpertEncoding => true
PdfCustomEncoding(base, _) => base.pdf_text_has_macexpert_base()
PdfFillUndefinedWithStandard(base) => base.pdf_text_has_macexpert_base()
_ => false
}
}
///|
fn PdfFont::pdf_text_has_macexpert_base(self : PdfFont) -> Bool {
match self {
PdfFontStandard(data) => data.encoding.pdf_text_has_macexpert_base()
PdfFontSimple(font) => font.encoding.pdf_text_has_macexpert_base()
PdfFontCIDKeyed(_) => false
}
}
///|
fn PdfFont::pdf_text_macexpert_duplicate_charcode(
self : PdfFont,
codepoint : Int,
) -> Int? {
if codepoint == 0xF6E6 && self.pdf_text_has_macexpert_base() {
Some(0x5F)
} else {
None
}
}
///|
fn pdf_text_notdef_name() -> PdfName {
pdf_text_name(".notdef")
}
///|
fn pdf_text_tounicode_glyphname(bytes : PdfBytes) -> PdfName {
let output : Array[Byte] = [47]
for byte in bytes {
output.push(byte)
}
pdf_name_of_bytes(Bytes::from_array(output))
}
///|
fn PdfTextExtractor::pdf_text_encoded_glyph_of_charcode(
self : PdfTextExtractor,
code : Int,
) -> PdfTextGlyph {
match self.font.pdf_text_glyphname_of_charcode(code) {
Some(glyphname) =>
match self.font.pdf_text_codepoints_of_glyphname(glyphname) {
Some(codepoints) => { glyphname, codepoints }
None => { glyphname, codepoints: [code] }
}
None => { glyphname: pdf_text_notdef_name(), codepoints: [code] }
}
}
///|
fn pdf_text_lookup_cmap_cid(map : ArrayView[(Int, Int)], code : Int) -> Int? {
for entry in map {
if entry.0 == code {
break Some(entry.1)
}
} nobreak {
None
}
}
///|
fn pdf_text_reverse_lookup_cmap_cid(
map : ArrayView[(Int, Int)],
cid : Int,
) -> Int? {
for entry in map {
if entry.1 == cid {
break Some(entry.0)
}
} nobreak {
None
}
}
///|
fn pdf_text_cmap_has_charcode(map : ArrayView[(Int, Int)], code : Int) -> Bool {
for entry in map {
if entry.0 == code {
break true
}
} nobreak {
false
}
}
///|
fn pdf_text_cmap_has_charcode_in_any(
first : ArrayView[(Int, Int)],
second : ArrayView[(Int, Int)],
code : Int,
) -> Bool {
pdf_text_cmap_has_charcode(first, code) ||
pdf_text_cmap_has_charcode(second, code)
}
///|
fn pdf_text_parsed_cmap_has_explicit_charcode(
parsed : PdfParsedCMap,
code : Int,
) -> Bool {
pdf_text_tounicode_has_charcode(parsed.map, code) ||
pdf_text_cmap_has_charcode_in_any(parsed.cid_map, parsed.notdef_map, code)
}
///|
fn PdfFont::pdf_text_external_cmap_codepoints(
self : PdfFont,
code : Int,
) -> Array[Int]? {
match self {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfExternalCMap(_, parsed) =>
match pdf_text_lookup_cmap_cid(parsed.cid_map, code) {
Some(cid) => Some([cid])
None =>
match pdf_text_lookup_cmap_cid(parsed.notdef_map, code) {
Some(cid) => Some([cid])
None =>
match pdf_text_lookup_tounicode_codepoints(parsed.map, code) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_parsed_cmap_predefined_base(parsed) {
Some(name) => {
let base_font : PdfFont = PdfFontCIDKeyed({
..font,
encoding: PdfPredefinedCMap(name),
})
match
base_font.pdf_text_predefined_builtin_codepoints(
code,
) {
Some(codepoints) => Some(codepoints)
None => None
}
}
None =>
if pdf_text_parsed_cmap_has_identity_base(parsed) &&
code >= 0 &&
code <= 0xFFFF {
Some([code])
} else {
None
}
}
}
}
}
_ => None
}
_ => None
}
}
///|
fn pdf_text_external_cmap_codepoints_from_lookup(
font : PdfCIDKeyedFont,
parsed : PdfParsedCMap,
lookup : PdfTextExternalCMapLookup,
code : Int,
) -> Array[Int]? {
match lookup.cid_map.get(code) {
Some(cid) => Some([cid])
None =>
match lookup.notdef_map.get(code) {
Some(cid) => Some([cid])
None =>
match lookup.map.get(code) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_parsed_cmap_predefined_base(parsed) {
Some(name) => {
let base_font : PdfFont = PdfFontCIDKeyed({
..font,
encoding: PdfPredefinedCMap(name),
})
base_font.pdf_text_predefined_builtin_codepoints(code)
}
None =>
if pdf_text_parsed_cmap_has_identity_base(parsed) &&
code >= 0 &&
code <= 0xFFFF {
Some([code])
} else {
None
}
}
}
}
}
}
///|
fn PdfFont::pdf_text_external_cmap_charcode(self : PdfFont, cid : Int) -> Int? {
match self {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfExternalCMap(_, parsed) =>
match pdf_text_reverse_lookup_cmap_cid(parsed.cid_map, cid) {
Some(code) => Some(code)
None =>
match pdf_text_reverse_lookup_cmap_cid(parsed.notdef_map, cid) {
Some(code) =>
if pdf_text_cmap_has_charcode(parsed.cid_map, code) {
None
} else {
Some(code)
}
None =>
match
pdf_text_reverse_lookup_tounicode_charcode(
parsed.map,
cid,
parsed.cid_map,
parsed.notdef_map,
) {
Some(code) => Some(code)
None =>
match pdf_text_parsed_cmap_predefined_base(parsed) {
Some(name) => {
let base_font : PdfFont = PdfFontCIDKeyed({
..font,
encoding: PdfPredefinedCMap(name),
})
match
base_font.pdf_text_predefined_builtin_charcode(cid) {
Some(code) =>
if pdf_text_parsed_cmap_has_explicit_charcode(
parsed, code,
) {
None
} else {
Some(code)
}
None => None
}
}
None =>
if pdf_text_parsed_cmap_has_identity_base(parsed) &&
cid >= 0 &&
cid <= 0xFFFF &&
!pdf_text_parsed_cmap_has_explicit_charcode(
parsed, cid,
) {
Some(cid)
} else {
None
}
}
}
}
}
_ => None
}
_ => None
}
}
///|
fn PdfFont::pdf_text_predefined_builtin_codepoints(
self : PdfFont,
code : Int,
) -> Array[Int]? {
match self {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfPredefinedCMap(name) =>
match pdf_text_predefined_direct_unicode_codepoints(name, code) {
Some(codepoints) => Some(codepoints)
None =>
match pdf_text_predefined_japan1_builtin_codepoints(name, code) {
Some(codepoints) => Some(codepoints)
None =>
if pdf_text_predefined_cmap_uses_shift_jis_charcodes(name) {
match pdf_text_predefined_rksj_single_byte_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
} else if pdf_text_predefined_cmap_uses_gb_euc_charcodes(name) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_gb1_vertical_codepoint_table(name),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match pdf_text_predefined_gb_euc_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
}
} else if pdf_text_predefined_cmap_uses_gbpc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_gb1_vertical_codepoint_table(name),
code,
) {
Some(codepoint) => Some([codepoint])
None => pdf_text_predefined_gbpc_euc_codepoints(code)
}
} else {
match
pdf_text_predefined_cns1_builtin_codepoints(name, code) {
Some(codepoints) => Some(codepoints)
None =>
if pdf_text_predefined_cmap_uses_uhc_charcodes(name) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_korea1_vertical_codepoint_table(
name,
),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match pdf_text_predefined_uhc_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
}
} else if pdf_text_predefined_cmap_uses_ksc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_korea1_vertical_codepoint_table(
name,
),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match
pdf_text_predefined_ksc_euc_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
}
} else if pdf_text_predefined_cmap_uses_kscpc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_korea1_vertical_codepoint_table(
name,
),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
pdf_text_predefined_kscpc_euc_codepoints(code)
}
} else if pdf_text_predefined_cmap_uses_gbk2k_charcodes(
name,
) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_gb1_vertical_codepoint_table(
name,
),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match pdf_text_predefined_gbk2k_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
}
} else if pdf_text_predefined_cmap_uses_gbk_charcodes(
name,
) {
match
pdf_text_predefined_vertical_codepoint(
pdf_text_predefined_gb1_vertical_codepoint_table(
name,
),
code,
) {
Some(codepoint) => Some([codepoint])
None =>
match pdf_text_predefined_gbk_codepoint(code) {
Some(codepoint) => Some([codepoint])
None => None
}
}
} else {
None
}
}
}
}
}
_ => None
}
_ => None
}
}
///|
fn PdfFont::pdf_text_predefined_builtin_charcode(
self : PdfFont,
codepoint : Int,
) -> Int? {
match self {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfPredefinedCMap(name) =>
match pdf_text_predefined_direct_unicode_charcode(name, codepoint) {
Some(code) => Some(code)
None =>
match
pdf_text_predefined_japan1_builtin_charcode(name, codepoint) {
Some(code) => Some(code)
None =>
if pdf_text_predefined_cmap_uses_shift_jis_charcodes(name) {
pdf_text_predefined_rksj_single_byte_charcode(codepoint)
} else if pdf_text_predefined_cmap_uses_gb_euc_charcodes(name) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_gb1_vertical_charcode_table(name),
codepoint,
) {
Some(code) => Some(code)
None => pdf_text_predefined_gb_euc_charcode(codepoint)
}
} else if pdf_text_predefined_cmap_uses_gbpc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_gb1_vertical_charcode_table(name),
codepoint,
) {
Some(code) => Some(code)
None => pdf_text_predefined_gbpc_euc_charcode(codepoint)
}
} else {
match
pdf_text_predefined_cns1_builtin_charcode(name, codepoint) {
Some(code) => Some(code)
None =>
if pdf_text_predefined_cmap_uses_uhc_charcodes(name) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_korea1_vertical_charcode_table(
name,
),
codepoint,
) {
Some(code) => Some(code)
None => pdf_text_predefined_uhc_charcode(codepoint)
}
} else if pdf_text_predefined_cmap_uses_ksc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_korea1_vertical_charcode_table(
name,
),
codepoint,
) {
Some(code) => Some(code)
None =>
pdf_text_predefined_ksc_euc_charcode(codepoint)
}
} else if pdf_text_predefined_cmap_uses_kscpc_euc_charcodes(
name,
) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_korea1_vertical_charcode_table(
name,
),
codepoint,
) {
Some(code) => Some(code)
None =>
pdf_text_predefined_kscpc_euc_charcode(codepoint)
}
} else if pdf_text_predefined_cmap_uses_gbk2k_charcodes(
name,
) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_gb1_vertical_charcode_table(
name,
),
codepoint,
) {
Some(code) => Some(code)
None =>
pdf_text_predefined_gbk2k_charcode(codepoint)
}
} else if pdf_text_predefined_cmap_uses_gbk_charcodes(
name,
) {
match
pdf_text_predefined_vertical_charcode(
pdf_text_predefined_gb1_vertical_charcode_table(
name,
),
codepoint,
) {
Some(code) => Some(code)
None => pdf_text_predefined_gbk_charcode(codepoint)
}
} else {
None
}
}
}
}
}
_ => None
}
_ => None
}
}
///|
fn PdfTextExtractor::pdf_text_glyph_of_charcode(
self : PdfTextExtractor,
code : Int,
) -> PdfTextGlyph {
match self.font.pdf_text_tounicode() {
Some(tounicode) =>
match pdf_text_lookup_tounicode(tounicode, code) {
Some(bytes) =>
try pdf_codepoints_of_utf16be(bytes) catch {
_ => { glyphname: pdf_text_notdef_name(), codepoints: [code] }
} noraise {
codepoints =>
{ glyphname: pdf_text_tounicode_glyphname(bytes), codepoints }
}
None => { glyphname: pdf_text_notdef_name(), codepoints: [code] }
}
None =>
match self.font.pdf_text_predefined_builtin_codepoints(code) {
Some(codepoints) => { glyphname: pdf_text_notdef_name(), codepoints }
None =>
match self.font.pdf_text_external_cmap_codepoints(code) {
Some(codepoints) =>
{ glyphname: pdf_text_notdef_name(), codepoints }
None => self.pdf_text_encoded_glyph_of_charcode(code)
}
}
}
}
///|
fn pdf_text_push_two_byte_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
guard index + 1 < text.length() else { raise BadText }
output.push((text[index].to_int() << 8) | text[index + 1].to_int())
index + 2
}
///|
fn pdf_text_push_three_byte_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
guard index + 2 < text.length() else { raise BadText }
output.push(
(((text[index].to_int() << 8) | text[index + 1].to_int()) << 8) |
text[index + 2].to_int(),
)
index + 3
}
///|
fn pdf_text_push_four_byte_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
guard index + 3 < text.length() else { raise BadText }
output.push(
(
(
(((text[index].to_int() << 8) | text[index + 1].to_int()) << 8) |
text[index + 2].to_int()
) <<
8
) |
text[index + 3].to_int(),
)
index + 4
}
///|
fn pdf_text_push_utf8_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
let first = text[index].to_int()
let (length, code) = if first >> 7 == 0 {
(1, first)
} else if first >> 5 == 0b110 {
guard index + 1 < text.length() else { raise InvalidUTF8 }
(2, pdf_text_pack_two_bytes(first, text[index + 1].to_int()))
} else if first >> 4 == 0b1110 {
guard index + 2 < text.length() else { raise InvalidUTF8 }
(3, pdf_text_pack_bytes_as_charcode(text[index:index + 3]))
} else if first >> 3 == 0b11110 {
guard index + 3 < text.length() else { raise InvalidUTF8 }
(
4,
pdf_text_pack_four_bytes(
first,
text[index + 1].to_int(),
text[index + 2].to_int(),
text[index + 3].to_int(),
),
)
} else {
raise InvalidUTF8
}
guard pdf_text_predefined_utf8_codepoints(code) is Some(_) else {
raise InvalidUTF8
}
output.push(code)
index + length
}
///|
fn pdf_text_push_utf16_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
let first = pdf_text_pack_two_bytes(
text[index].to_int(),
text[index + 1].to_int(),
)
if first >= 0xD800 && first <= 0xDBFF {
guard index + 3 < text.length() else { raise InvalidUTF16BE }
let second = pdf_text_pack_two_bytes(
text[index + 2].to_int(),
text[index + 3].to_int(),
)
guard second >= 0xDC00 && second <= 0xDFFF else { raise InvalidUTF16BE }
output.push(
pdf_text_pack_four_bytes(
first >> 8,
first & 0xFF,
second >> 8,
second & 0xFF,
),
)
index + 4
} else if first >= 0xDC00 && first <= 0xDFFF {
raise InvalidUTF16BE
} else {
output.push(first)
index + 2
}
}
///|
fn pdf_text_push_utf32_charcode(
output : Array[Int],
text : BytesView,
index : Int,
) -> Int raise PdfError {
guard index + 3 < text.length() else { raise BadText }
let code = pdf_text_pack_four_bytes(
text[index].to_int(),
text[index + 1].to_int(),
text[index + 2].to_int(),
text[index + 3].to_int(),
)
guard pdf_text_valid_unicode_codepoint(code) else {
raise InvalidUnicodeCodepoint(code)
}
output.push(code)
index + 4
}
///|
fn pdf_text_shift_jis_lead_byte(byte : Int) -> Bool {
(byte >= 0x81 && byte <= 0x9F) || (byte >= 0xE0 && byte <= 0xFC)
}
///|
fn pdf_text_gbk2k_four_byte_prefix(first : Int, second : Int) -> Bool {
first >= 0x81 && first <= 0xFE && second >= 0x30 && second <= 0x39
}
///|
fn pdf_text_predefined_mixed_byte_charcodes(
name : PdfName,
text : BytesView,
) -> Array[Int] raise PdfError {
let output : Array[Int] = []
let shift_jis = pdf_text_predefined_cmap_uses_shift_jis_charcodes(name)
let b5pc = pdf_text_predefined_cmap_uses_b5pc_charcodes(name)
let cns1_b5 = pdf_text_predefined_cmap_uses_cns1_b5_charcodes(name)
let cns_euc = pdf_text_predefined_cmap_uses_cns_euc_charcodes(name)
let hkscs = pdf_text_predefined_cmap_uses_hkscs_charcodes(name)
let gbpc_euc = pdf_text_predefined_cmap_uses_gbpc_euc_charcodes(name)
let hojo_euc = pdf_text_predefined_cmap_uses_hojo_euc_charcodes(name)
let ksc_euc = pdf_text_predefined_cmap_uses_ksc_euc_charcodes(name)
let kscpc_euc = pdf_text_predefined_cmap_uses_kscpc_euc_charcodes(name)
let gbk2k = pdf_text_predefined_cmap_uses_gbk2k_charcodes(name)
let gbk = pdf_text_predefined_cmap_uses_gbk_charcodes(name)
let mut index = 0
while index < text.length() {
let first = text[index].to_int()
if shift_jis {
if pdf_text_shift_jis_lead_byte(first) {
index = pdf_text_push_two_byte_charcode(output, text, index)
} else {
output.push(first)
index += 1
}
} else if hojo_euc {
index = pdf_text_push_three_byte_charcode(output, text, index)
} else if gbk2k &&
index + 1 < text.length() &&
pdf_text_gbk2k_four_byte_prefix(first, text[index + 1].to_int()) {
index = pdf_text_push_four_byte_charcode(output, text, index)
} else if cns_euc && first == 0x8E {
index = pdf_text_push_four_byte_charcode(output, text, index)
} else if first < 0x80 ||
(cns_euc && first == 0x80) ||
(
b5pc &&
(
first == 0x80 ||
(first >= 0x83 && first <= 0xA0) ||
(first >= 0xFD && first <= 0xFF)
)
) ||
(
gbpc_euc &&
(
first == 0x80 ||
(first >= 0x83 && first <= 0xA0) ||
(first >= 0xFD && first <= 0xFF)
)
) ||
(ksc_euc && first == 0x80) ||
(
kscpc_euc &&
((first >= 0x80 && first <= 0x9F) || first == 0xFE || first == 0xFF)
) ||
(cns1_b5 && first == 0x80) ||
(hkscs && first == 0x80) ||
(gbk && (first == 0x80 || first == 0xFF)) {
output.push(first)
index += 1
} else {
index = pdf_text_push_two_byte_charcode(output, text, index)
}
}
output
}
///|
fn pdf_text_predefined_cmap_charcodes_of_text(
name : PdfName,
text : BytesView,
) -> Array[Int] raise PdfError {
if pdf_text_predefined_cmap_uses_utf8_charcodes(name) {
let output : Array[Int] = []
let mut index = 0
while index < text.length() {
index = pdf_text_push_utf8_charcode(output, text, index)
}
output
} else if pdf_text_predefined_cmap_uses_utf16_charcodes(name) {
guard text.length() % 2 == 0 else { raise BadText }
let output : Array[Int] = []
let mut index = 0
while index < text.length() {
index = pdf_text_push_utf16_charcode(output, text, index)
}
output
} else if pdf_text_predefined_cmap_uses_utf32_charcodes(name) {
guard text.length() % 4 == 0 else { raise BadText }
let output : Array[Int] = []
let mut index = 0
while index < text.length() {
index = pdf_text_push_utf32_charcode(output, text, index)
}
output
} else if pdf_text_predefined_cmap_uses_mixed_byte_charcodes(name) {
pdf_text_predefined_mixed_byte_charcodes(name, text)
} else {
let output : Array[Int] = []
if name == pdf_text_identity_h_name ||
name == pdf_text_identity_v_name ||
pdf_text_predefined_cmap_uses_two_byte_charcodes(name) {
guard text.length() % 2 == 0 else { raise BadText }
let mut index = 0
while index < text.length() {
index = pdf_text_push_two_byte_charcode(output, text, index)
}
} else {
for byte in text {
output.push(byte.to_int())
}
}
output
}
}
///|
fn PdfFont::pdf_text_charcodes_of_text(
self : PdfFont,
text : BytesView,
) -> Array[Int] raise PdfError {
match self {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfPredefinedCMap(name) =>
pdf_text_predefined_cmap_charcodes_of_text(name, text)
PdfExternalCMap(_, parsed) =>
pdf_text_parsed_cmap_charcodes_of_text(parsed, text)
_ => self.pdf_text_fixed_or_single_byte_charcodes_of_text(text)
}
_ => self.pdf_text_fixed_or_single_byte_charcodes_of_text(text)
}
}
///|
fn PdfFont::pdf_text_fixed_or_single_byte_charcodes_of_text(
self : PdfFont,
text : BytesView,
) -> Array[Int] raise PdfError {
let output : Array[Int] = []
if self.uses_two_byte_codes() {
guard text.length() % 2 == 0 else { raise BadText }
let mut index = 0
while index < text.length() {
index = pdf_text_push_two_byte_charcode(output, text, index)
}
} else {
for byte in text {
output.push(byte.to_int())
}
}
output
}
///|
/// Resolve glyph names and Unicode codepoints for each character code in text.
///
/// This lower-level extractor exposes both sides of the mapping. The input is
/// a PDF text byte sequence, not a MoonBit `String`, and malformed byte
/// segmentation raises `PdfError`.
pub fn PdfTextExtractor::glyphnames_and_codepoints_of_text(
self : PdfTextExtractor,
text : BytesView,
) -> Array[PdfTextGlyph] raise PdfError {
[
for code in self.font.pdf_text_charcodes_of_text(text) => {
self.pdf_text_glyph_of_charcode(code)
}
]
}
///|
fn PdfTextExtractor::pdf_text_external_cmap_codepoints_of_text(
self : PdfTextExtractor,
font : PdfCIDKeyedFont,
parsed : PdfParsedCMap,
text : BytesView,
) -> Array[Int] raise PdfError {
let lookup = pdf_text_external_cmap_lookup(parsed)
let output : Array[Int] = []
for code in pdf_text_parsed_cmap_charcodes_of_text(parsed, text) {
let codepoints = match
pdf_text_external_cmap_codepoints_from_lookup(font, parsed, lookup, code) {
Some(codepoints) => codepoints
None => self.pdf_text_encoded_glyph_of_charcode(code).codepoints
}
for codepoint in codepoints {
output.push(codepoint)
}
}
output
}
///|
fn PdfTextExtractor::pdf_text_tounicode_codepoints_of_text(
self : PdfTextExtractor,
tounicode : ArrayView[(Int, PdfBytes)],
text : BytesView,
) -> Array[Int] raise PdfError {
let lookup = pdf_text_tounicode_codepoints_lookup_map(tounicode)
let output : Array[Int] = []
for code in self.font.pdf_text_charcodes_of_text(text) {
match lookup.get(code) {
Some(codepoints) =>
for codepoint in codepoints {
output.push(codepoint)
}
None => output.push(code)
}
}
output
}
///|
fn PdfTextExtractor::pdf_text_regular_codepoints_of_text(
self : PdfTextExtractor,
text : BytesView,
) -> Array[Int] raise PdfError {
let output : Array[Int] = []
for code in self.font.pdf_text_charcodes_of_text(text) {
for codepoint in self.pdf_text_glyph_of_charcode(code).codepoints {
output.push(codepoint)
}
}
output
}
///|
/// Extract Unicode codepoints from PDF text bytes.
///
/// `/ToUnicode` mappings take precedence. External CMaps, predefined CMaps,
/// glyph names, and font-specific fallbacks are used when no explicit
/// ToUnicode mapping exists. Multi-codepoint glyph names are flattened into
/// the returned array.
pub fn PdfTextExtractor::codepoints_of_text(
self : PdfTextExtractor,
text : BytesView,
) -> Array[Int] raise PdfError {
match self.font.pdf_text_tounicode() {
Some(tounicode) =>
self.pdf_text_tounicode_codepoints_of_text(tounicode, text)
None =>
match self.font {
PdfFontCIDKeyed(font) =>
match font.encoding {
PdfExternalCMap(_, parsed) =>
self.pdf_text_external_cmap_codepoints_of_text(font, parsed, text)
_ => self.pdf_text_regular_codepoints_of_text(text)
}
_ => self.pdf_text_regular_codepoints_of_text(text)
}
}
}
///|
/// Resolve only glyph names from PDF text bytes.
///
/// This bypasses Unicode conversion and is useful for callers that need the
/// encoded glyph identity rather than extracted text.
pub fn PdfTextExtractor::glyphnames_of_text(
self : PdfTextExtractor,
text : BytesView,
) -> Array[PdfName] raise PdfError {
[
for code in self.font.pdf_text_charcodes_of_text(text) => {
self.pdf_text_glyph_of_charcode(code).glyphname
}
]
}
///|
/// Compatibility wrapper for `PdfTextExtractor::codepoints_of_text`.
pub fn pdf_codepoints_of_text(
extractor : PdfTextExtractor,
text : BytesView,
) -> Array[Int] raise PdfError {
extractor.codepoints_of_text(text)
}
///|
/// Compatibility wrapper for `PdfTextExtractor::glyphnames_of_text`.
pub fn pdf_glyphnames_of_text(
extractor : PdfTextExtractor,
text : BytesView,
) -> Array[PdfName] raise PdfError {
extractor.glyphnames_of_text(text)
}
///|
/// Return a PDF character code that can encode one Unicode codepoint.
///
/// The lookup prefers explicit ToUnicode reverse mappings, then predefined or
/// external CMap reverse lookup, then simple-font glyph names. `None` means
/// the current font has no known single-codepoint representation.
pub fn PdfTextExtractor::charcode_of_codepoint(
self : PdfTextExtractor,
codepoint : Int,
) -> Int? {
match self.font.pdf_text_tounicode() {
Some(tounicode) =>
for entry in tounicode {
try pdf_codepoints_of_utf16be(entry.1) catch {
_ => ()
} noraise {
[single] if single == codepoint => break Some(entry.0)
_ => ()
}
} nobreak {
None
}
None =>
match self.font.pdf_text_predefined_builtin_charcode(codepoint) {
Some(code) => Some(code)
None =>
match self.font.pdf_text_external_cmap_charcode(codepoint) {
Some(code) => Some(code)
None =>
for code in 0..<256 {
match self.font.pdf_text_glyphname_of_charcode(code) {
Some(glyphname) =>
if self.font.pdf_text_glyphname_has_single_codepoint(
glyphname, codepoint,
) {
break Some(code)
}
_ => ()
}
} nobreak {
self.font.pdf_text_macexpert_duplicate_charcode(codepoint)
}
}
}
}
}
///|
/// Read a font dictionary and build a pure Unicode-to-charcode closure.
///
/// `debug` is accepted for CamlPDF API compatibility; this implementation
/// preserves pure lookup behavior and does not write missing-glyph diagnostics.
pub fn pdf_charcode_extractor_of_font(
document : PdfDocument,
font : PdfObject,
debug? : Bool = false,
) -> ((Int) -> Int?) raise PdfError {
pdf_charcode_extractor_of_font_real(document.read_font(font), debug~)
}
///|
/// Write a custom encoding dictionary and return its object number.
///
/// Currently this supports `/Differences` over an implicit base encoding, which
/// is the form needed by the font writer. Unsupported encodings raise
/// `PdfError::EncodingWriteUnsupported`.
pub fn PdfDocument::write_encoding(
self : PdfDocument,
encoding : PdfEncoding,
) -> Int raise PdfError {
match encoding {
PdfCustomEncoding(PdfImplicitInFontFile, differences) => {
let values : Array[PdfObject] = []
for difference in differences {
values.push(PdfInteger(difference.code))
values.push(PdfNameObject(difference.name))
}
self.add_object(
PdfDictionary([
(pdf_text_type_key_name, PdfNameObject(pdf_text_encoding_key_name)),
(pdf_text_differences_key_name, PdfArray(values)),
]),
)
}
_ => raise EncodingWriteUnsupported
}
}
///|
/// Build a simple Type 1 font dictionary for a base font and named encoding.
///
/// Only encodings with a direct PDF name can be written this way; custom or
/// implicit encodings raise `PdfError::EncodingWriteUnsupported`.
pub fn pdf_make_font(
fontname : PdfName,
encoding : PdfEncoding,
) -> PdfObject raise PdfError {
match encoding.pdf_name() {
Some(encoding_name) =>
PdfDictionary([
(pdf_text_type_key_name, PdfNameObject(pdf_text_font_name)),
(pdf_text_subtype_key_name, PdfNameObject(pdf_text_type1_name)),
(pdf_text_encoding_key_name, PdfNameObject(encoding_name)),
(pdf_text_base_font_key_name, PdfNameObject(fontname)),
])
None => raise EncodingWriteUnsupported
}
}
///|
fn pdf_text_rectangle_object(rectangle : PdfRectangle) -> PdfObject {
PdfArray([
PdfReal(rectangle.min_x),
PdfReal(rectangle.min_y),
PdfReal(rectangle.max_x),
PdfReal(rectangle.max_y),
])
}
///|
fn pdf_text_type3_charprocs_object(
charprocs : ArrayView[(PdfName, PdfObject)],
) -> PdfObject {
PdfDictionary([ for entry in charprocs => entry ])
}
///|
fn pdf_text_type3_resources_entries(
resources : PdfObject,
) -> Array[(PdfName, PdfObject)] {
match resources {
PdfDictionary(entries) if entries.length() == 0 => []
_ => [(pdf_text_resources_key_name, resources)]
}
}
///|
fn pdf_text_type3_metrics_entries(
firstchar : Int,
lastchar : Int,
widths : ArrayView[Int],
) -> Array[(PdfName, PdfObject)] {
if widths.length() == 0 {
[
(pdf_text_first_char_key_name, PdfInteger(0)),
(pdf_text_last_char_key_name, PdfInteger(0)),
(pdf_text_widths_key_name, PdfArray([PdfReal(0.0)])),
]
} else {
[
(pdf_text_first_char_key_name, PdfInteger(firstchar)),
(pdf_text_last_char_key_name, PdfInteger(lastchar)),
(
pdf_text_widths_key_name,
PdfArray([ for width in widths => PdfInteger(width) ]),
),
]
}
}
///|
fn PdfDocument::pdf_text_type3_encoding_entries(
self : PdfDocument,
encoding : PdfEncoding,
) -> Array[(PdfName, PdfObject)] raise PdfError {
match encoding {
PdfImplicitInFontFile => []
_ =>
[(pdf_text_encoding_key_name, PdfIndirect(self.write_encoding(encoding)))]
}
}
///|
fn PdfDocument::pdf_text_make_type3_font(
self : PdfDocument,
data : PdfType3Glyphs,
firstchar : Int,
lastchar : Int,
widths : ArrayView[Int],
encoding : PdfEncoding,
) -> PdfObject raise PdfError {
PdfDictionary(
[
(pdf_text_type_key_name, PdfNameObject(pdf_text_font_name)),
(pdf_text_subtype_key_name, PdfNameObject(pdf_text_type3_name)),
(pdf_text_font_bbox_key_name, pdf_text_rectangle_object(data.fontbbox)),
(pdf_text_font_matrix_key_name, pdf_object_of_matrix(data.fontmatrix)),
(
pdf_text_charprocs_key_name,
pdf_text_type3_charprocs_object(data.charprocs),
),
..pdf_text_type3_resources_entries(data.resources),
..pdf_text_type3_metrics_entries(firstchar, lastchar, widths),
..self.pdf_text_type3_encoding_entries(encoding),
],
)
}
///|
fn pdf_text_integer_of_double(value : Double) -> PdfObject {
PdfInteger(value.to_int())
}
///|
fn pdf_text_font_descriptor_bbox_object(fontbbox : PdfRectangle) -> PdfObject {
PdfArray([
pdf_text_integer_of_double(fontbbox.min_x),
pdf_text_integer_of_double(fontbbox.min_y),
pdf_text_integer_of_double(fontbbox.max_x),
pdf_text_integer_of_double(fontbbox.max_y),
])
}
///|
fn pdf_text_fontfile2_number(fontfile : PdfFontFile?) -> Int? {
match fontfile {
Some(PdfFontFile2(number)) => Some(number)
_ => None
}
}
///|
fn pdf_text_true_type_encoding_name(encoding : PdfEncoding) -> PdfName? {
match encoding {
PdfFillUndefinedWithStandard(base) => base.pdf_name()
_ => encoding.pdf_name()
}
}
///|
fn pdf_text_tounicode_preamble() -> String {
"/CIDInit /ProcSet findresource begin\n" +
"12 dict begin\n" +
"begincmap\n" +
"/CIDSystemInfo <<\n" +
" /Registry (Adobe)\n" +
" /Ordering (UCS)\n" +
" /Supplement 0\n" +
">> def\n" +
"/CMapName /Adobe-Identity-UCS def\n" +
"/CMapType 2 def\n" +
"1 begincodespacerange\n" +
"<00>\n" +
"endcodespacerange\n"
}
///|
fn pdf_text_tounicode_postamble() -> String {
"endbfrange\n" +
"endcmap\n" +
"CMapName currentdict /CMap defineresource pop\n" +
"end\n" +
"end\n"
}
///|
fn pdf_text_tounicode_sorted(
entries : ArrayView[(Int, PdfBytes)],
) -> Array[(Int, PdfBytes)] {
let sorted = [ for entry in entries => entry ]
sorted.sort_by(fn(left, right) { left.0.compare(right.0) })
sorted
}
///|
fn pdf_text_hex_int_min2(value : Int) -> String {
let text = value.to_string(radix=16)
if text.length() == 1 {
"0" + text
} else {
text
}
}
///|
fn pdf_text_ascii_length(text : String) -> Int {
@ascii.encode(text).length()
}
///|
fn pdf_text_write_ascii(
output : Array[Byte],
position : Int,
text : String,
) -> Int {
let mut current = position
for byte in @ascii.encode(text) {
output[current] = byte
current += 1
}
current
}
///|
fn pdf_text_hex_bytes_length(bytes : BytesView) -> Int {
bytes.length() * 2
}
///|
fn pdf_text_write_hex_bytes(
output : Array[Byte],
position : Int,
bytes : BytesView,
) -> Int {
let mut current = position
for byte in bytes {
let value = byte.to_int()
output[current] = pdf_writer_hex_digit(value / 16)
output[current + 1] = pdf_writer_hex_digit(value % 16)
current += 2
}
current
}
///|
fn pdf_text_tounicode_bfrange_length(
charcode_text : String,
bytes : BytesView,
) -> Int {
pdf_text_ascii_length("<") +
pdf_text_ascii_length(charcode_text) +
pdf_text_ascii_length("><") +
pdf_text_ascii_length(charcode_text) +
pdf_text_ascii_length("><") +
pdf_text_hex_bytes_length(bytes) +
pdf_text_ascii_length(">\n")
}
///|
fn pdf_text_write_tounicode_bfrange(
output : Array[Byte],
position : Int,
charcode_text : String,
bytes : BytesView,
) -> Int {
let mut current = pdf_text_write_ascii(output, position, "<")
current = pdf_text_write_ascii(output, current, charcode_text)
current = pdf_text_write_ascii(output, current, "><")
current = pdf_text_write_ascii(output, current, charcode_text)
current = pdf_text_write_ascii(output, current, "><")
current = pdf_text_write_hex_bytes(output, current, bytes)
pdf_text_write_ascii(output, current, ">\n")
}
///|
fn pdf_text_tounicode_bytes(sorted : ArrayView[(Int, PdfBytes)]) -> PdfBytes {
let count_text = sorted.length().to_string()
let mut length = pdf_text_ascii_length(pdf_text_tounicode_preamble()) +
pdf_text_ascii_length(count_text) +
pdf_text_ascii_length(" beginbfrange\n") +
pdf_text_ascii_length(pdf_text_tounicode_postamble())
let mut charcode = 33
let charcode_texts : Array[String] = Array::new(capacity=sorted.length())
for entry in sorted {
let charcode_text = pdf_text_hex_int_min2(charcode)
length += pdf_text_tounicode_bfrange_length(charcode_text, entry.1)
charcode_texts.push(charcode_text)
charcode += 1
}
let output = Array::make(length, b'\x00')
let mut position = pdf_text_write_ascii(
output,
0,
pdf_text_tounicode_preamble(),
)
position = pdf_text_write_ascii(output, position, count_text)
position = pdf_text_write_ascii(output, position, " beginbfrange\n")
for index, entry in sorted {
position = pdf_text_write_tounicode_bfrange(
output,
position,
charcode_texts[index],
entry.1,
)
}
let _ = pdf_text_write_ascii(output, position, pdf_text_tounicode_postamble())
Bytes::from_array(output)
}
///|
fn PdfDocument::pdf_text_write_tounicode(
self : PdfDocument,
entries : ArrayView[(Int, PdfBytes)],
) -> Int {
let sorted = pdf_text_tounicode_sorted(entries)
let bytes = pdf_text_tounicode_bytes(sorted)
self.add_object(
pdf_stream(
PdfDictionary([(pdf_text_length_key_name, PdfInteger(bytes.length()))]),
StreamGot(bytes),
),
)
}
///|
fn PdfDocument::pdf_text_make_true_type_font(
self : PdfDocument,
basefont : PdfName,
firstchar : Int,
lastchar : Int,
widths : Array[Int],
descriptor : PdfFontDescriptor,
encoding : PdfEncoding,
) -> PdfObject raise PdfError {
let ttf = match pdf_text_fontfile2_number(descriptor.fontfile) {
Some(number) => number
None => raise FontWriteUnsupported
}
let fontdescriptor = PdfDictionary([
(pdf_text_type_key_name, PdfNameObject(pdf_text_font_descriptor_key_name)),
(pdf_text_font_name_key_name, PdfNameObject(basefont)),
(pdf_text_flags_key_name, PdfInteger(descriptor.flags)),
(
pdf_text_font_bbox_key_name,
pdf_text_font_descriptor_bbox_object(descriptor.fontbbox),
),
(
pdf_text_italic_angle_key_name,
pdf_text_integer_of_double(descriptor.italicangle),
),
(pdf_text_ascent_key_name, pdf_text_integer_of_double(descriptor.ascent)),
(pdf_text_descent_key_name, pdf_text_integer_of_double(descriptor.descent)),
(
pdf_text_cap_height_key_name,
pdf_text_integer_of_double(descriptor.capheight),
),
(pdf_text_stemv_key_name, pdf_text_integer_of_double(descriptor.stemv)),
(pdf_text_xheight_key_name, pdf_text_integer_of_double(descriptor.xheight)),
(
pdf_text_avg_width_key_name,
pdf_text_integer_of_double(descriptor.avgwidth),
),
(
pdf_text_max_width_key_name,
pdf_text_integer_of_double(descriptor.maxwidth),
),
(pdf_text_font_file2_key_name, PdfIndirect(ttf)),
])
let fontdescriptor_number = self.add_object(fontdescriptor)
let tounicode_entry = match descriptor.tounicode {
Some(tounicode) =>
[
(
pdf_text_tounicode_key_name,
PdfIndirect(self.pdf_text_write_tounicode(tounicode)),
),
]
None => {
let encoding_name = match pdf_text_true_type_encoding_name(encoding) {
Some(name) => name
None => raise EncodingWriteUnsupported
}
[(pdf_text_encoding_key_name, PdfNameObject(encoding_name))]
}
}
PdfDictionary(
[
(pdf_text_type_key_name, PdfNameObject(pdf_text_font_name)),
(pdf_text_subtype_key_name, PdfNameObject(pdf_text_true_type_name_value)),
(pdf_text_base_font_key_name, PdfNameObject(basefont)),
(pdf_text_font_descriptor_key_name, PdfIndirect(fontdescriptor_number)),
(pdf_text_first_char_key_name, PdfInteger(firstchar)),
(pdf_text_last_char_key_name, PdfInteger(lastchar)),
(
pdf_text_widths_key_name,
PdfArray([ for width in widths => PdfInteger(width) ]),
),
..tounicode_entry,
],
)
}
///|
fn PdfDocument::pdf_text_add_font_object(
self : PdfDocument,
object : PdfObject,
objnum : Int?,
) -> Int {
match objnum {
Some(number) => {
self.add_object_given_number(number, object)
number
}
None => self.add_object(object)
}
}
///|
/// Write a parsed font into the document and return its object number.
///
/// Standard fonts, Type 3 fonts with descriptors, and TrueType fonts with
/// descriptors are supported. `objnum` can force the destination object number
/// for rewrite workflows. Unsupported font shapes raise `PdfError::FontWriteUnsupported`.
pub fn PdfDocument::write_font(
self : PdfDocument,
font : PdfFont,
objnum? : Int? = None,
) -> Int raise PdfError {
match font {
PdfFontStandard({ font, encoding }) =>
self.pdf_text_add_font_object(
pdf_make_font(font.pdf_name(), encoding),
objnum,
)
PdfFontSimple(
{
fonttype: PdfType3(data),
firstchar,
lastchar,
widths,
encoding,
fontdescriptor,
..,
}
) =>
match fontdescriptor {
Some(_) =>
self.pdf_text_add_font_object(
self.pdf_text_make_type3_font(
data, firstchar, lastchar, widths, encoding,
),
objnum,
)
None => raise FontWriteUnsupported
}
PdfFontSimple(
{
fonttype: PdfTrueType,
basefont: Some(basefont),
firstchar,
lastchar,
widths,
fontdescriptor: Some(descriptor),
encoding,
..,
}
) =>
self.pdf_text_add_font_object(
self.pdf_text_make_true_type_font(
basefont, firstchar, lastchar, widths, descriptor, encoding,
),
objnum,
)
_ => raise FontWriteUnsupported
}
}
///|
/// Compatibility wrapper for `PdfDocument::write_font`.
pub fn pdf_write_font(
document : PdfDocument,
font : PdfFont,
objnum? : Int? = None,
) -> Int raise PdfError {
document.write_font(font, objnum~)
}
///|
/// Test whether a PDF string starts with the UTF-16BE byte-order mark.
///
/// PDF "Unicode strings" are byte strings beginning with `FE FF`; the input is
/// intentionally a `BytesView` rather than a MoonBit `String`.
pub fn pdf_is_unicode_string(bytes : BytesView) -> Bool {
bytes.length() >= 2 && bytes[0].to_int() == 0xFE && bytes[1].to_int() == 0xFF
}
///|
fn pdf_text_write_utf16be_unit(
output : Array[Byte],
position : Int,
value : Int,
) -> Int raise PdfError {
output[position] = pdf_byte_of_int((value >> 8) & 0xFF)
output[position + 1] = pdf_byte_of_int(value & 0xFF)
position + 2
}
///|
fn pdf_text_utf16be_codepoint_length(codepoint : Int) -> Int raise PdfError {
pdf_text_check_unicode_codepoint(codepoint)
if codepoint < 0x10000 {
2
} else {
4
}
}
///|
fn pdf_text_write_utf16be_codepoint(
output : Array[Byte],
position : Int,
codepoint : Int,
) -> Int raise PdfError {
pdf_text_check_unicode_codepoint(codepoint)
if codepoint < 0x10000 {
pdf_text_write_utf16be_unit(output, position, codepoint)
} else {
let shifted = codepoint - 0x10000
let current = pdf_text_write_utf16be_unit(
output,
position,
0xD800 | (shifted >> 10),
)
pdf_text_write_utf16be_unit(output, current, 0xDC00 | (shifted & 0x3FF))
}
}
///|
/// Encode Unicode scalar values as a PDF UTF-16BE string with BOM.
///
/// Invalid scalar values, including surrogate codepoints, raise
/// `PdfError::InvalidUnicodeCodepoint`.
pub fn pdf_utf16be_of_codepoints(
codepoints : ArrayView[Int],
) -> PdfBytes raise PdfError {
let mut length = 2
for codepoint in codepoints {
length += pdf_text_utf16be_codepoint_length(codepoint)
}
let output = Array::make(length, b'\x00')
output[0] = pdf_byte_of_int(0xFE)
output[1] = pdf_byte_of_int(0xFF)
let mut position = 2
for codepoint in codepoints {
position = pdf_text_write_utf16be_codepoint(output, position, codepoint)
}
Bytes::from_array(output)
}
///|
fn pdf_text_utf16be_unit(bytes : BytesView, index : Int) -> Int raise PdfError {
guard index + 1 < bytes.length() else { raise InvalidUTF16BE }
(bytes[index].to_int() << 8) | bytes[index + 1].to_int()
}
///|
/// Decode UTF-16BE bytes into Unicode scalar values.
///
/// The input should not include the leading `FE FF` BOM; callers that receive a
/// PDF Unicode string normally pass `bytes[2:]`. Odd lengths, lone surrogates,
/// and malformed pairs raise `PdfError::InvalidUTF16BE`.
pub fn pdf_codepoints_of_utf16be(
bytes : BytesView,
) -> Array[Int] raise PdfError {
let codepoints : Array[Int] = []
let mut index = 0
while index < bytes.length() {
let w1 = pdf_text_utf16be_unit(bytes, index)
index += 2
if w1 >= 0xD800 && w1 <= 0xDBFF {
let w2 = pdf_text_utf16be_unit(bytes, index)
guard w2 >= 0xDC00 && w2 <= 0xDFFF else { raise InvalidUTF16BE }
index += 2
codepoints.push((((w1 & 0x3FF) << 10) | (w2 & 0x3FF)) + 0x10000)
} else if w1 >= 0xDC00 && w1 <= 0xDFFF {
raise InvalidUTF16BE
} else {
codepoints.push(w1)
}
}
codepoints
}
///|
fn pdf_text_check_unicode_codepoint(codepoint : Int) -> Unit raise PdfError {
if codepoint < 0 ||
codepoint > 0x10FFFF ||
(codepoint >= 0xD800 && codepoint <= 0xDFFF) {
raise InvalidUnicodeCodepoint(codepoint)
}
}
///|
fn pdf_text_utf8_codepoint_length(codepoint : Int) -> Int raise PdfError {
pdf_text_check_unicode_codepoint(codepoint)
if codepoint <= 0x7F {
1
} else if codepoint <= 0x7FF {
2
} else if codepoint <= 0xFFFF {
3
} else {
4
}
}
///|
fn pdf_text_write_utf8_codepoint(
output : Array[Byte],
position : Int,
codepoint : Int,
) -> Int raise PdfError {
pdf_text_check_unicode_codepoint(codepoint)
if codepoint <= 0x7F {
output[position] = pdf_byte_of_int(codepoint)
position + 1
} else if codepoint <= 0x7FF {
output[position] = pdf_byte_of_int((codepoint >> 6) | 0xC0)
output[position + 1] = pdf_byte_of_int((codepoint & 0x3F) | 0x80)
position + 2
} else if codepoint <= 0xFFFF {
output[position] = pdf_byte_of_int((codepoint >> 12) | 0xE0)
output[position + 1] = pdf_byte_of_int(((codepoint >> 6) & 0x3F) | 0x80)
output[position + 2] = pdf_byte_of_int((codepoint & 0x3F) | 0x80)
position + 3
} else {
output[position] = pdf_byte_of_int((codepoint >> 18) | 0xF0)
output[position + 1] = pdf_byte_of_int(((codepoint >> 12) & 0x3F) | 0x80)
output[position + 2] = pdf_byte_of_int(((codepoint >> 6) & 0x3F) | 0x80)
output[position + 3] = pdf_byte_of_int((codepoint & 0x3F) | 0x80)
position + 4
}
}
///|
/// Encode Unicode scalar values as UTF-8 bytes.
///
/// Invalid scalar values, including surrogate codepoints, raise
/// `PdfError::InvalidUnicodeCodepoint`.
pub fn pdf_utf8_of_codepoints(
codepoints : ArrayView[Int],
) -> PdfBytes raise PdfError {
let mut length = 0
for codepoint in codepoints {
length += pdf_text_utf8_codepoint_length(codepoint)
}
let output = Array::make(length, b'\x00')
let mut position = 0
for codepoint in codepoints {
position = pdf_text_write_utf8_codepoint(output, position, codepoint)
}
Bytes::from_array(output)
}
///|
fn pdf_text_is_utf8_continuation(byte : Int) -> Bool {
byte >> 6 == 0b10
}
///|
fn pdf_text_push_utf8_codepoint(
output : Array[Int],
codepoint : Int,
min_codepoint : Int,
) -> Unit raise PdfError {
pdf_text_check_unicode_codepoint(codepoint)
guard codepoint >= min_codepoint else { raise InvalidUTF8 }
output.push(codepoint)
}
///|
/// Decode UTF-8 bytes into Unicode scalar values.
///
/// Overlong encodings, invalid continuation bytes, truncated sequences, and
/// surrogate or out-of-range scalar values raise `PdfError::InvalidUTF8` or
/// `PdfError::InvalidUnicodeCodepoint`.
pub fn pdf_codepoints_of_utf8(bytes : BytesView) -> Array[Int] raise PdfError {
let output : Array[Int] = []
let mut index = 0
while index < bytes.length() {
let first = bytes[index].to_int()
if first >> 7 == 0 {
output.push(first)
index += 1
} else if first >> 5 == 0b110 {
guard index + 1 < bytes.length() else { raise InvalidUTF8 }
let b1 = bytes[index + 1].to_int()
guard pdf_text_is_utf8_continuation(b1) else { raise InvalidUTF8 }
pdf_text_push_utf8_codepoint(
output,
((first & 0x1F) << 6) | (b1 & 0x3F),
0x80,
)
index += 2
} else if first >> 4 == 0b1110 {
guard index + 2 < bytes.length() else { raise InvalidUTF8 }
let b1 = bytes[index + 1].to_int()
let b2 = bytes[index + 2].to_int()
guard pdf_text_is_utf8_continuation(b1) &&
pdf_text_is_utf8_continuation(b2) else {
raise InvalidUTF8
}
pdf_text_push_utf8_codepoint(
output,
((first & 0x0F) << 12) | ((b1 & 0x3F) << 6) | (b2 & 0x3F),
0x800,
)
index += 3
} else if first >> 3 == 0b11110 {
guard index + 3 < bytes.length() else { raise InvalidUTF8 }
let b1 = bytes[index + 1].to_int()
let b2 = bytes[index + 2].to_int()
let b3 = bytes[index + 3].to_int()
guard pdf_text_is_utf8_continuation(b1) &&
pdf_text_is_utf8_continuation(b2) &&
pdf_text_is_utf8_continuation(b3) else {
raise InvalidUTF8
}
pdf_text_push_utf8_codepoint(
output,
((first & 0x07) << 18) |
((b1 & 0x3F) << 12) |
((b2 & 0x3F) << 6) |
(b3 & 0x3F),
0x10000,
)
index += 4
} else {
raise InvalidUTF8
}
}
output
}
///|
fn pdf_codepoint_of_pdfdocencoding_byte_option(value : Int) -> Int? {
match value {
0x09 => Some(0x0009)
0x0A => Some(0x000A)
0x0C => Some(0x000C)
0x0D => Some(0x000D)
0x18 => Some(0x02D8)
0x19 => Some(0x02C7)
0x1A => Some(0x02C6)
0x1B => Some(0x02D9)
0x1C => Some(0x02DD)
0x1D => Some(0x02DB)
0x1E => Some(0x02DA)
0x1F => Some(0x02DC)
0x20..=0x7E => Some(value)
0x80 => Some(0x2022)
0x81 => Some(0x2020)
0x82 => Some(0x2021)
0x83 => Some(0x2026)
0x84 => Some(0x2014)
0x85 => Some(0x2013)
0x86 => Some(0x0192)
0x87 => Some(0x2044)
0x88 => Some(0x2039)
0x89 => Some(0x203A)
0x8A => Some(0x2212)
0x8B => Some(0x2030)
0x8C => Some(0x201E)
0x8D => Some(0x201C)
0x8E => Some(0x201D)
0x8F => Some(0x2018)
0x90 => Some(0x2019)
0x91 => Some(0x201A)
0x92 => Some(0x2122)
0x93 => Some(0xFB02)
0x95 => Some(0x0141)
0x96 => Some(0x0152)
0x97 => Some(0x0160)
0x98 => Some(0x0178)
0x99 => Some(0x017D)
0x9A => Some(0x0131)
0x9B => Some(0x0142)
0x9C => Some(0x0153)
0x9D => Some(0x0161)
0x9E => Some(0x017E)
0xA0 => Some(0x20AC)
0xA1..=0xAC => Some(value)
0xAE..=0xFF => Some(value)
_ => None
}
}
///|
/// Decode one PDFDocEncoding byte to a Unicode codepoint.
///
/// Undefined byte values raise `PdfError::InvalidPDFDocEncoding`.
pub fn pdf_codepoint_of_pdfdocencoding_byte(value : Int) -> Int raise PdfError {
match pdf_codepoint_of_pdfdocencoding_byte_option(value) {
Some(codepoint) => codepoint
None => raise InvalidPDFDocEncoding(value)
}
}
///|
/// Decode a PDFDocEncoding byte string to Unicode codepoints.
pub fn pdf_codepoints_of_pdfdocencoding(
bytes : BytesView,
) -> Array[Int] raise PdfError {
let codepoints : Array[Int] = []
for byte in bytes {
codepoints.push(pdf_codepoint_of_pdfdocencoding_byte(byte.to_int()))
}
codepoints
}
///|
/// Return the PDFDocEncoding byte for a Unicode codepoint, if representable.
///
/// The lookup preserves CamlPDF compatibility for the `fi` ligature by mapping
/// U+FB01 to byte `0x93`.
pub fn pdf_pdfdocencoding_byte_of_codepoint(codepoint : Int) -> Byte? {
if codepoint == 0xFB01 {
Some(0x93)
} else {
for value in 0..<=255 {
match pdf_codepoint_of_pdfdocencoding_byte_option(value) {
Some(decoded) if decoded == codepoint => break Some(value.to_byte())
_ => ()
}
} nobreak {
None
}
}
}
///|
/// Encode codepoints as PDFDocEncoding when every scalar is representable.
///
/// Returns `None` instead of falling back to UTF-16BE; use
/// `pdf_pdfdocstring_of_codepoints` for the PDF string policy fallback.
pub fn pdf_pdfdocencoding_of_codepoints(
codepoints : ArrayView[Int],
) -> PdfBytes? {
let output = Array::make(codepoints.length(), b'\x00')
for index in 0.. output[index] = byte
None => return None
}
}
Some(Bytes::from_array(output))
}
///|
/// Encode codepoints as a PDF string.
///
/// PDFDocEncoding is used when all codepoints are representable; otherwise the
/// result is a BOM-prefixed UTF-16BE string.
pub fn pdf_pdfdocstring_of_codepoints(
codepoints : ArrayView[Int],
) -> PdfBytes raise PdfError {
match pdf_pdfdocencoding_of_codepoints(codepoints) {
Some(encoded) => encoded
None => pdf_utf16be_of_codepoints(codepoints)
}
}
///|
/// Decode a PDF string to Unicode codepoints.
///
/// BOM-prefixed strings are treated as UTF-16BE. Other byte strings are
/// decoded as PDFDocEncoding.
pub fn pdf_codepoints_of_pdfdocstring(
bytes : BytesView,
) -> Array[Int] raise PdfError {
if pdf_is_unicode_string(bytes) {
pdf_codepoints_of_utf16be(bytes[2:])
} else {
pdf_codepoints_of_pdfdocencoding(bytes)
}
}
///|
/// Convert a PDF string byte sequence to UTF-8 bytes.
pub fn pdf_utf8_of_pdfdocstring(bytes : BytesView) -> PdfBytes raise PdfError {
pdf_utf8_of_codepoints(pdf_codepoints_of_pdfdocstring(bytes))
}
///|
/// Convert UTF-8 bytes to the compact PDF string representation.
///
/// The result uses PDFDocEncoding when possible and UTF-16BE otherwise.
pub fn pdf_pdfdocstring_of_utf8(bytes : BytesView) -> PdfBytes raise PdfError {
pdf_pdfdocstring_of_codepoints(pdf_codepoints_of_utf8(bytes))
}
///|
/// Re-encode a UTF-16BE PDF string using PDFDocEncoding when possible.
///
/// Non-Unicode input is returned as an owned copy. Malformed UTF-16BE raises
/// `PdfError::InvalidUTF16BE`.
pub fn pdf_simplify_utf16be(bytes : BytesView) -> PdfBytes raise PdfError {
if pdf_is_unicode_string(bytes) {
pdf_pdfdocstring_of_codepoints(pdf_codepoints_of_pdfdocstring(bytes))
} else {
bytes.to_owned()
}
}