OrgGo/unipdf
1
0
Fork 0
mirror of https://github.com/unidoc/unipdf.git synced 2025-04-27 13:48:51 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Use StandardEncoding for builtin standard fonts (not WinAnsiEncoding). Fix testcases.

Browse Source 
Add test cases and fix the encoding table also based on observed errors
This commit is contained in:
Gunnsteinn Hall 2019-03-26 00:57:10 +00:00
parent 936bf446fc
commit ee1416433c
5 changed files with 27 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pdf/extractor/text_test.go
View File

@ -218,7 +218,7 @@ var fileExtractionTests = []struct {
{filename: "/rfc6962.txt.pdf",
expectedPageText: map[int][]string{
4: []string{
"timestamps for certificates they then don't log",
"timestamps for certificates they then don’t log",
`The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD",`},
},
},

8
pdf/internal/textencoding/simple_pdf.go
View File

@ -97,7 +97,7 @@ var standardCharToRune = map[byte]rune{ // 149 entries
0x4d: 'M', 0x4e: 'N', 0x4f: 'O', 0x50: 'P', 0x51: 'Q',
0x52: 'R', 0x53: 'S', 0x54: 'T', 0x55: 'U', 0x56: 'V',
0x57: 'W', 0x58: 'X', 0x59: 'Y', 0x5a: 'Z', 0x5b: '[',
0x5c: '\\', 0x5d: ']', 0x5e: '^', 0x5f: '_', 0x60: '`',
0x5c: '\\', 0x5d: ']', 0x5e: '^', 0x5f: '_', 0x60: '‘',
0x61: 'a', 0x62: 'b', 0x63: 'c', 0x64: 'd', 0x65: 'e',
0x66: 'f', 0x67: 'g', 0x68: 'h', 0x69: 'i', 0x6a: 'j',
0x6b: 'k', 0x6c: 'l', 0x6d: 'm', 0x6e: 'n', 0x6f: 'o',
@ -112,7 +112,7 @@ var standardCharToRune = map[byte]rune{ // 149 entries
0xbc: '…', 0xbd: '‰', 0xbf: '¿', 0xc1: '`', 0xc2: '´',
0xc3: 'ˆ', 0xc4: '˜', 0xc5: '¯', 0xc6: '˘', 0xc7: '˙',
0xc8: '¨', 0xca: '˚', 0xcb: '¸', 0xcc: '˝', 0xcd: '˛',
0xce: 'ˇ', 0xcf: '—', 0xe0: 'Æ', 0xe2: 'ª', 0xe7: 'Ł',
0xe8: 'Ø', 0xe9: 'Œ', 0xea: 'º', 0xf0: 'æ', 0xf5: 'ı',
0xf7: 'ł', 0xf8: 'ø', 0xf9: 'œ', 0xfa: 'ß',
0xce: 'ˇ', 0xcf: '—', 0xe1: 'Æ', 0xe3: 'ª', 0xe8: 'Ł',
0xe9: 'Ø', 0xea: 'Œ', 0xeb: 'º', 0xf1: 'æ', 0xf5: 'ı',
0xf8: 'ł', 0xf9: 'ø', 0xfa: 'œ', 0xfb: 'ß',
}

19
pdf/model/font_test.go
View File

@ -344,7 +344,7 @@ func TestFontDescriptor(t *testing.T) {
}
var charcodeBytesToUnicodeTest = []fontFragmentTest{
{"Helvetica built-in",
{"Helvetica WinAnsiEncoding",
"./testdata/font/simple.txt", 1,
[]byte{32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52,
53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74,
@ -362,6 +362,19 @@ var charcodeBytesToUnicodeTest = []fontFragmentTest{
"abcdefghijklmnopqrstuvwxyz{|}~€‚ƒ„…†‡ˆ‰Š‹OEŽ‘’“”•–—˜™š›oežŸ¡¢£¤¥¦§¨©ª«¬®¯°±²³´µ¶·" +
"¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞfzàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ",
},
{"Helvetica built-in",
"./testdata/font/simple.txt", 5,
[]byte{
32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58,
59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85,
86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109,
110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126,
161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 177, 178, 179, 180, 182, 183,
184, 185, 186, 187, 188, 189, 191, 193, 194, 195, 196, 197, 198, 199, 225, 227, 232, 241, 245, 248, 249,
250, 251},
` !"#$%&’()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_‘abcdefghijklmnopqrstuvwxyz{|}~` +
`¡¢£⁄¥ƒ§¤'“«‹›fifl–†‡·¶•‚„”»…‰¿` + "`" + `´ˆ˜¯˘˙ƪŁæıłøoefz`,
},
{"Symbol built-in",
"./testdata/font/simple.txt", 3,
[]byte{32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52,
@ -436,8 +449,8 @@ var charcodeBytesToUnicodeTest = []fontFragmentTest{
},
{"Type1 font with /Encoding with /Differences",
"./testdata/font/noise-invariant.txt", 102,
[]byte{96, 247, 39, 32, 147, 231, 148, 32, 232, 32, 193, 111, 180, 32, 105, 116,
169, 115, 32, 204, 195, 196, 197, 198, 199, 168, 202, 206, 226, 234, 172, 245, 173, 151,
[]byte{96, 248, 39, 32, 147, 232, 148, 32, 233, 32, 193, 111, 180, 32, 105, 116,
169, 115, 32, 204, 195, 196, 197, 198, 199, 168, 202, 206, 227, 235, 172, 245, 173, 151,
177, 151, 178, 179, 183, 185, 188, 205, 184, 189},
"‘ł’ “Ł” Ø `o´ it's ˝ˆ˜¯˘˙¨˚ˇªº‹ı›—–—†‡•„…˛¸‰",
},

6
pdf/model/internal/fonts/std.go
View File

@ -76,11 +76,9 @@ type StdFont struct {
encoder textencoding.TextEncoder
}
// NewStdFont returns a new instance of the font with a default encoder set (WinAnsiEncoding).
// TODO(gunnsth): Create test cases to verify that the default encoder is WinAnsiEncoding or StandardEncoding.
// NewStdFont returns a new instance of the font with a default encoder set (StandardEncoding).
func NewStdFont(desc Descriptor, metrics map[rune]CharMetrics) StdFont {
enc := textencoding.NewWinAnsiEncoder() // Default
return NewStdFontWithEncoding(desc, metrics, enc)
return NewStdFontWithEncoding(desc, metrics, textencoding.NewStandardEncoder())
}
// NewStdFontWithEncoding returns a new instance of the font with a specified encoder.

5
pdf/model/testdata/font/simple.txt vendored
View File

@ -1,5 +1,5 @@
1 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>
endobj
2 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /Courier >>
@ -10,3 +10,6 @@ endobj
4 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /ZapfDingbats >>
endobj
5 0 obj
<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>
endobj