File: test_pdfbase_ttfonts.py

package info (click to toggle)
python-reportlab 1.20debian-1
  • links: PTS
  • area: main
  • in suites: sarge
  • size: 6,068 kB
  • ctags: 5,801
  • sloc: python: 53,293; xml: 1,494; makefile: 85
file content (372 lines) | stat: -rw-r--r-- 15,580 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372

"""Test TrueType font subsetting & embedding code.

This test uses a sample font by Dustin Norlander (Dustismo_Roman.ttf).
The font is free and can be distributed under the terms of the GPL.
"""

import string
from cStringIO import StringIO

from reportlab.test import unittest
from reportlab.test.utils import makeSuiteForClasses, outputfile

from reportlab.pdfgen.canvas import Canvas
from reportlab.pdfbase import pdfmetrics
from reportlab.pdfbase.pdfdoc import PDFDocument, PDFError
from reportlab.pdfbase.ttfonts import TTFont, TTFontFace, TTFontFile, TTFOpenFile, \
                                      TTFontParser, TTFontMaker, TTFError, \
                                      parse_utf8, makeToUnicodeCMap, \
                                      FF_SYMBOLIC, FF_NONSYMBOLIC, \
                                      calcChecksum, add32, _L2U32


def utf8(code):
    "Convert a given UCS character index into UTF-8"
    if code < 0 or code > 0x7FFFFFFF:
        raise ValueError, 'Invalid UCS character 0x%x' % code
    elif code < 0x00000080:
        return chr(code)
    elif code < 0x00000800:
        return '%c%c' % \
                 (0xC0 + (code >> 6),
                  0x80 + (code & 0x3F))
    elif code < 0x00010000:
        return '%c%c%c' % \
                 (0xE0 + (code >> 12),
                  0x80 + ((code >> 6) & 0x3F),
                  0x80 + (code & 0x3F))
    elif code < 0x00200000:
        return '%c%c%c%c' % \
                 (0xF0 + (code >> 18),
                  0x80 + ((code >> 12) & 0x3F),
                  0x80 + ((code >> 6) & 0x3F),
                  0x80 + (code & 0x3F))
    elif code < 0x04000000:
        return '%c%c%c%c%c' % \
                 (0xF8 + (code >> 24),
                  0x80 + ((code >> 18) & 0x3F),
                  0x80 + ((code >> 12) & 0x3F),
                  0x80 + ((code >> 6) & 0x3F),
                  0x80 + (code & 0x3F))
    else:
        return '%c%c%c%c%c%c' % \
                 (0xFC + (code >> 30),
                  0x80 + ((code >> 24) & 0x3F),
                  0x80 + ((code >> 18) & 0x3F),
                  0x80 + ((code >> 12) & 0x3F),
                  0x80 + ((code >> 6) & 0x3F),
                  0x80 + (code & 0x3F))

def _simple_subset_generation(fn,npages,alter=0):
    c = Canvas(outputfile(fn))
    c.setFont('Helvetica', 30)
    c.drawString(100,700, 'Unicode TrueType Font Test %d pages' % npages)
    # Draw a table of Unicode characters
    for p in xrange(npages):
        for fontName in ('TestFont','PenguinFont'):
            c.setFont(fontName, 10)
            for i in xrange(32):
                for j in xrange(32):
                    ch = utf8(i * 32 + j+p*alter)
                    c.drawString(80 + j * 13 + int(j / 16) * 4, 600 - i * 13 - int(i / 8) * 8, ch)
        c.showPage()
    c.save()

class TTFontsTestCase(unittest.TestCase):
    "Make documents with TrueType fonts"

    def testTTF(self):
        "Test PDF generation with TrueType fonts"
        pdfmetrics.registerFont(TTFont("TestFont", "Dustismo_Roman.ttf"))
        pdfmetrics.registerFont(TTFont("PenguinFont", "PenguinAttack.ttf"))
        _simple_subset_generation('test_pdfbase_ttfonts1.pdf',1)
        _simple_subset_generation('test_pdfbase_ttfonts3.pdf',3)
        _simple_subset_generation('test_pdfbase_ttfonts35.pdf',3,5)

        # Do it twice with the same font object
        c = Canvas(outputfile('test_pdfbase_ttfontsadditional.pdf'))
        # Draw a table of Unicode characters
        c.setFont('TestFont', 10)
        c.drawString(100, 700, 'Hello, ' + utf8(0xffee))
        c.save()


class TTFontFileTestCase(unittest.TestCase):
    "Tests TTFontFile, TTFontParser and TTFontMaker classes"

    def testFontFileFailures(self):
        "Tests TTFontFile constructor error checks"
        self.assertRaises(TTFError, TTFontFile, "nonexistent file")
        self.assertRaises(TTFError, TTFontFile, StringIO(""))
        self.assertRaises(TTFError, TTFontFile, StringIO("invalid signature"))
        self.assertRaises(TTFError, TTFontFile, StringIO("OTTO - OpenType not supported yet"))
        self.assertRaises(TTFError, TTFontFile, StringIO("\0\1\0\0"))

    def testFontFileReads(self):
        "Tests TTFontParset.read_xxx"

        class FakeTTFontFile(TTFontParser):
            def __init__(self, data):
                self._ttf_data = data
                self._pos = 0

        ttf = FakeTTFontFile("\x81\x02\x03\x04" "\x85\x06" "ABCD" "\x7F\xFF" "\x80\x00" "\xFF\xFF")
        self.assertEquals(ttf.read_ulong(), _L2U32(0x81020304L)) # big-endian
        self.assertEquals(ttf._pos, 4)
        self.assertEquals(ttf.read_ushort(), 0x8506)
        self.assertEquals(ttf._pos, 6)
        self.assertEquals(ttf.read_tag(), 'ABCD')
        self.assertEquals(ttf._pos, 10)
        self.assertEquals(ttf.read_short(), 0x7FFF)
        self.assertEquals(ttf.read_short(), -0x8000)
        self.assertEquals(ttf.read_short(), -1)

    def testFontFile(self):
        "Tests TTFontFile and TTF parsing code"
        ttf = TTFontFile("Dustismo_Roman.ttf")
        self.assertEquals(ttf.name, "DustismoRoman")
        self.assertEquals(ttf.flags, FF_SYMBOLIC)
        self.assertEquals(ttf.italicAngle, 0.0)
        self.assertEquals(ttf.ascent, 712)
        self.assertEquals(ttf.descent, -238)
        self.assertEquals(ttf.capHeight, 712)
        self.assertEquals(ttf.bbox, [-113, -256, 923, 1051])
        self.assertEquals(ttf.stemV, 87)
        self.assertEquals(ttf.defaultWidth, 500)

    def testAdd32(self):
        "Test add32"
        self.assertEquals(add32(10, -6), 4)
        self.assertEquals(add32(6, -10), -4)
        self.assertEquals(add32(_L2U32(0x80000000L), -1), 0x7FFFFFFF)
        self.assertEquals(add32(0x7FFFFFFF, 1), _L2U32(0x80000000L))

    def testChecksum(self):
        "Test calcChecksum function"
        self.assertEquals(calcChecksum(""), 0)
        self.assertEquals(calcChecksum("\1"), 0x01000000)
        self.assertEquals(calcChecksum("\x01\x02\x03\x04\x10\x20\x30\x40"), 0x11223344)
        self.assertEquals(calcChecksum("\x81"), _L2U32(0x81000000L))
        self.assertEquals(calcChecksum("\x81\x02"), _L2U32(0x81020000L))
        self.assertEquals(calcChecksum("\x81\x02\x03"), _L2U32(0x81020300L))
        self.assertEquals(calcChecksum("\x81\x02\x03\x04"), _L2U32(0x81020304L))
        self.assertEquals(calcChecksum("\x81\x02\x03\x04\x05"), _L2U32(0x86020304L))
        self.assertEquals(calcChecksum("\x41\x02\x03\x04\xD0\x20\x30\x40"), 0x11223344)
        self.assertEquals(calcChecksum("\xD1\x02\x03\x04\x40\x20\x30\x40"), 0x11223344)
        self.assertEquals(calcChecksum("\x81\x02\x03\x04\x90\x20\x30\x40"), 0x11223344)
        self.assertEquals(calcChecksum("\x7F\xFF\xFF\xFF\x00\x00\x00\x01"), _L2U32(0x80000000L))

    def testFontFileChecksum(self):
        "Tests TTFontFile and TTF parsing code"
        file = TTFOpenFile("Dustismo_Roman.ttf")[1].read()
        TTFontFile(StringIO(file), validate=1) # should not fail
        file1 = file[:12345] + "\xFF" + file[12346:] # change one byte
        self.assertRaises(TTFError, TTFontFile, StringIO(file1), validate=1)
        file1 = file[:8] + "\xFF" + file[9:] # change one byte
        self.assertRaises(TTFError, TTFontFile, StringIO(file1), validate=1)

    def testSubsetting(self):
        "Tests TTFontFile and TTF parsing code"
        ttf = TTFontFile("Dustismo_Roman.ttf")
        subset = ttf.makeSubset([0x41, 0x42])
        subset = TTFontFile(StringIO(subset), 0)
        for tag in ('cmap', 'head', 'hhea', 'hmtx', 'maxp', 'name', 'OS/2',
                    'post', 'cvt ', 'fpgm', 'glyf', 'loca', 'prep'):
            self.assert_(subset.get_table(tag))

        subset.seek_table('loca')
        for n in range(4):
            pos = subset.read_ushort()    # this is actually offset / 2
            self.failIf(pos % 2 != 0, "glyph %d at +%d should be long aligned" % (n, pos * 2))

        self.assertEquals(subset.name, "DustismoRoman")
        self.assertEquals(subset.flags, FF_SYMBOLIC)
        self.assertEquals(subset.italicAngle, 0.0)
        self.assertEquals(subset.ascent, 712)
        self.assertEquals(subset.descent, -238)
        self.assertEquals(subset.capHeight, 712)
        self.assertEquals(subset.bbox, [-113, -256, 923, 1051])
        self.assertEquals(subset.stemV, 87)

    def testFontMaker(self):
        "Tests TTFontMaker class"
        ttf = TTFontMaker()
        ttf.add("ABCD", "xyzzy")
        ttf.add("QUUX", "123")
        ttf.add("head", "12345678xxxx")
        stm = ttf.makeStream()
        ttf = TTFontParser(StringIO(stm), 0)
        self.assertEquals(ttf.get_table("ABCD"), "xyzzy")
        self.assertEquals(ttf.get_table("QUUX"), "123")


class TTFontFaceTestCase(unittest.TestCase):
    "Tests TTFontFace class"

    def testAddSubsetObjects(self):
        "Tests TTFontFace.addSubsetObjects"
        face = TTFontFace("Dustismo_Roman.ttf")
        doc = PDFDocument()
        fontDescriptor = face.addSubsetObjects(doc, "TestFont", [ 0x78, 0x2017 ])
        fontDescriptor = doc.idToObject[fontDescriptor.name].dict
        self.assertEquals(fontDescriptor['Type'], '/FontDescriptor')
        self.assertEquals(fontDescriptor['Ascent'], face.ascent)
        self.assertEquals(fontDescriptor['CapHeight'], face.capHeight)
        self.assertEquals(fontDescriptor['Descent'], face.descent)
        self.assertEquals(fontDescriptor['Flags'], (face.flags & ~FF_NONSYMBOLIC) | FF_SYMBOLIC)
        self.assertEquals(fontDescriptor['FontName'], "/TestFont")
        self.assertEquals(fontDescriptor['FontBBox'].sequence, face.bbox)
        self.assertEquals(fontDescriptor['ItalicAngle'], face.italicAngle)
        self.assertEquals(fontDescriptor['StemV'], face.stemV)
        fontFile = fontDescriptor['FontFile2']
        fontFile = doc.idToObject[fontFile.name]
        self.assert_(fontFile.content != "")


class TTFontTestCase(unittest.TestCase):
    "Tests TTFont class"

    def testParseUTF8(self):
        "Tests parse_utf8"
        self.assertEquals(parse_utf8(""), [])
        for i in range(0, 0x80):
            self.assertEquals(parse_utf8(chr(i)), [i])
        for i in range(0x80, 0xA0):
            self.assertRaises(ValueError, parse_utf8, chr(i))
        self.assertEquals(parse_utf8("abc"), [0x61, 0x62, 0x63])
        self.assertEquals(parse_utf8("\xC2\xA9x"), [0xA9, 0x78])
        self.assertEquals(parse_utf8("\xE2\x89\xA0x"), [0x2260, 0x78])
        self.assertRaises(ValueError, parse_utf8, "\xE2\x89x")
        # for i in range(0, 0xFFFF): - overkill
        for i in range(0x80, 0x200) + range(0x300, 0x400) + [0xFFFE, 0xFFFF]:
            self.assertEquals(parse_utf8(utf8(i)), [i])

    def testStringWidth(self):
        "Test TTFont.stringWidth"
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        self.assert_(font.stringWidth("test", 10) > 0)
        width = font.stringWidth(utf8(0x2260) * 2, 1000)
        expected = font.face.getCharWidth(0x2260) * 2
        self.assert_(abs(width - expected) < 0.01, "%g != %g" % (width, expected))

    def testSplitString(self):
        "Tests TTFont.splitString"
        doc = PDFDocument()
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        text = string.join(map(utf8, range(0, 512)), "")
        allchars = string.join(map(chr, range(0, 256)), "")
        chunks = [(0, allchars), (1, allchars)]
        self.assertEquals(font.splitString(text, doc), chunks)
        # Do it twice
        self.assertEquals(font.splitString(text, doc), chunks)

        text = string.join(map(utf8, range(511, -1, -1)), "")
        allchars = string.join(map(chr, range(255, -1, -1)), "")
        chunks = [(1, allchars), (0, allchars)]
        self.assertEquals(font.splitString(text, doc), chunks)

    def testSubsetInternalName(self):
        "Tests TTFont.getSubsetInternalName"
        doc = PDFDocument()
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        # Actually generate some subsets
        text = string.join(map(utf8, range(0, 513)), "")
        font.splitString(text, doc)
        self.assertRaises(IndexError, font.getSubsetInternalName, -1, doc)
        self.assertRaises(IndexError, font.getSubsetInternalName, 3, doc)
        self.assertEquals(font.getSubsetInternalName(0, doc), "/F1+0")
        self.assertEquals(font.getSubsetInternalName(1, doc), "/F1+1")
        self.assertEquals(font.getSubsetInternalName(2, doc), "/F1+2")
        self.assertEquals(doc.delayedFonts, [font])

    def testAddObjectsEmpty(self):
        "TTFont.addObjects should not fail when no characters were used"
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        doc = PDFDocument()
        font.addObjects(doc)

    def no_longer_testAddObjectsResets(self):
        "Test that TTFont.addObjects resets the font"
        # Actually generate some subsets
        doc = PDFDocument()
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        font.splitString('a', doc)            # create some subset
        doc = PDFDocument()
        font.addObjects(doc)
        self.assertEquals(font.frozen, 0)
        self.assertEquals(font.nextCode, 0)
        self.assertEquals(font.subsets, [])
        self.assertEquals(font.assignments, {})
        font.splitString('ba', doc)           # should work

    def testParallelConstruction(self):
        "Test that TTFont can be used for different documents at the same time"
        doc1 = PDFDocument()
        doc2 = PDFDocument()
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        self.assertEquals(font.splitString('ab', doc1), [(0, '\0\1')])
        self.assertEquals(font.splitString('b', doc2), [(0, '\0')])
        font.addObjects(doc1)
        self.assertEquals(font.splitString('c', doc2), [(0, '\1')])
        font.addObjects(doc2)

    def testAddObjects(self):
        "Test TTFont.addObjects"
        # Actually generate some subsets
        doc = PDFDocument()
        font = TTFont("TestFont", "Dustismo_Roman.ttf")
        font.splitString('a', doc)            # create some subset
        internalName = font.getSubsetInternalName(0, doc)[1:]
        font.addObjects(doc)
        pdfFont = doc.idToObject[internalName]
        self.assertEquals(doc.idToObject['BasicFonts'].dict[internalName], pdfFont)
        self.assertEquals(pdfFont.Name, internalName)
        self.assertEquals(pdfFont.BaseFont, "SUBSET+DustismoRoman+0")
        self.assertEquals(pdfFont.FirstChar, 0)
        self.assertEquals(pdfFont.LastChar, 0)
        self.assertEquals(len(pdfFont.Widths.sequence), 1)
        toUnicode = doc.idToObject[pdfFont.ToUnicode.name]
        self.assert_(toUnicode.content != "")
        fontDescriptor = doc.idToObject[pdfFont.FontDescriptor.name]
        self.assertEquals(fontDescriptor.dict['Type'], '/FontDescriptor')

    def testMakeToUnicodeCMap(self):
        "Test makeToUnicodeCMap"
        self.assertEquals(makeToUnicodeCMap("TestFont", [ 0x1234, 0x4321, 0x4242 ]),
"""/CIDInit /ProcSet findresource begin
12 dict begin
begincmap
/CIDSystemInfo
<< /Registry (TestFont)
/Ordering (TestFont)
/Supplement 0
>> def
/CMapName /TestFont def
/CMapType 2 def
1 begincodespacerange
<00> <02>
endcodespacerange
3 beginbfchar
<00> <1234>
<01> <4321>
<02> <4242>
endbfchar
endcmap
CMapName currentdict /CMap defineresource pop
end
end""")


def makeSuite():
    suite = makeSuiteForClasses(
        TTFontsTestCase,
        TTFontFileTestCase,
        TTFontFaceTestCase,
        TTFontTestCase)
    return suite


#noruntests
if __name__ == "__main__":
    unittest.TextTestRunner().run(makeSuite())