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
|
# pylint: disable=protected-access
from fpdf import FPDF
from fpdf.line_break import Fragment
PDF = FPDF()
GSTATE = PDF._get_current_graphics_state()
GSTATE_B = GSTATE.copy()
GSTATE_B.font_style = "B"
GSTATE_I = GSTATE.copy()
GSTATE_I.font_style = "I"
GSTATE_S = GSTATE.copy()
GSTATE_S.strikethrough = True
GSTATE_U = GSTATE.copy()
GSTATE_U.underline = True
GSTATE_BI = GSTATE.copy()
GSTATE_BI.font_style = "BI"
def merge_fragments(fragments):
"""
Helper function for testing the escaping characters
Will merge fragments that have different characters but same fragment.graphics_state
and same fragment.k and same fragment.link.
Example Input:
(
Fragment(characters=['a'], graphics_state={000}, k=1, link=None),
Fragment(characters=['b'], graphics_state={000}, k=1, link=None)
)
Example Output:
(Fragment(characters=['a', 'b'], graphics_state={000}, k=1, link=None))
"""
if not fragments:
return []
merged_fragments = []
current_fragment = fragments[0]
for fragment in fragments[1:]:
if (
fragment.graphics_state == current_fragment.graphics_state
and fragment.k == current_fragment.k
and fragment.link == current_fragment.link
):
current_fragment.characters.extend(fragment.characters)
else:
merged_fragments.append(current_fragment)
current_fragment = fragment
merged_fragments.append(current_fragment)
return tuple(merged_fragments)
def test_markdown_parse_simple_ok():
frags = tuple(
FPDF()._parse_chars(
"**bold**, __italics__, ~~strikethrough~~ and --underlined--", True
)
)
expected = (
Fragment("bold", GSTATE_B, k=PDF.k),
Fragment(", ", GSTATE, k=PDF.k),
Fragment("italics", GSTATE_I, k=PDF.k),
Fragment(", ", GSTATE, k=PDF.k),
Fragment("strikethrough", GSTATE_S, k=PDF.k),
Fragment(" and ", GSTATE, k=PDF.k),
Fragment("underlined", GSTATE_U, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_simple_ok_escaped():
frags = merge_fragments(
tuple(
FPDF()._parse_chars(
"\\**bold\\**, \\__italics\\__ and \\--underlined\\-- escaped", True
)
)
)
expected = (
Fragment("**bold**, __italics__ and --underlined-- escaped", GSTATE, k=PDF.k),
)
assert frags == expected
frags = merge_fragments(
tuple(
FPDF()._parse_chars(
r"raw \**bold\**, \__italics\__ and \--underlined\-- escaped", True
)
)
)
expected = (
Fragment(
"raw **bold**, __italics__ and --underlined-- escaped", GSTATE, k=PDF.k
),
)
assert frags == expected
frags = tuple(FPDF()._parse_chars("escape *\\*between marker*\\*", True))
expected = (Fragment("escape *\\*between marker*\\*", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(FPDF()._parse_chars("escape **\\after marker**\\", True))
expected = (
Fragment("escape ", GSTATE, k=PDF.k),
Fragment("\\after marker", GSTATE_B, k=PDF.k),
Fragment("\\", GSTATE, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_strikethrough_escaped():
frags = merge_fragments(tuple(FPDF()._parse_chars("\\~~strike\\~~", True)))
expected = (Fragment("~~strike~~", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_unrelated_escape():
frags = merge_fragments(
tuple(FPDF()._parse_chars("unrelated \\ escape \\**bold\\**", True))
)
expected = (Fragment("unrelated \\ escape **bold**", GSTATE, k=PDF.k),)
assert frags == expected
frags = merge_fragments(
tuple(FPDF()._parse_chars("unrelated \\\\ double escape \\**bold\\**", True))
)
expected = (Fragment("unrelated \\\\ double escape **bold**", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_parse_multiple_escape():
frags = merge_fragments(
tuple(FPDF()._parse_chars("\\\\**bold\\\\** double escaped", True))
)
expected = (
Fragment("\\\\", GSTATE, k=PDF.k),
Fragment("bold\\\\", GSTATE_B, k=PDF.k),
Fragment(" double escaped", GSTATE, k=PDF.k),
)
assert frags == expected
frags = merge_fragments(
tuple(FPDF()._parse_chars("\\\\\\**triple bold\\\\\\** escaped", True))
)
expected = (Fragment("\\\\**triple bold\\\\** escaped", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_parse_overlapping():
frags = tuple(FPDF()._parse_chars("**bold __italics__**", True))
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("italics", GSTATE_BI, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_overlapping_escaped():
frags = merge_fragments(
tuple(FPDF()._parse_chars("**bold \\__italics\\__**", True))
)
expected = (Fragment("bold __italics__", GSTATE_B, k=PDF.k),)
assert frags == expected
def test_markdown_parse_crossing_markers():
frags = merge_fragments(
tuple(FPDF()._parse_chars("**bold __and** italics__", True))
)
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("and", GSTATE_BI, k=PDF.k),
Fragment(" italics", GSTATE_I, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_crossing_markers_escaped():
frags = merge_fragments(
tuple(FPDF()._parse_chars("**bold __and\\** italics__", True))
)
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("and** italics", GSTATE_BI, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_unterminated():
frags = merge_fragments(tuple(FPDF()._parse_chars("**bold __italics__", True)))
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("italics", GSTATE_BI, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_unterminated_escaped():
frags = merge_fragments(tuple(FPDF()._parse_chars("**bold\\** __italics__", True)))
expected = (
Fragment("bold** ", GSTATE_B, k=PDF.k),
Fragment("italics", GSTATE_BI, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_line_of_markers():
frags = merge_fragments(tuple(FPDF()._parse_chars("*** woops", True)))
expected = (Fragment("*** woops", GSTATE, k=PDF.k),)
assert frags == expected
frags = merge_fragments(tuple(FPDF()._parse_chars("----------", True)))
expected = (Fragment("----------", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(FPDF()._parse_chars("****BOLD**", True))
expected = (Fragment("****BOLD", GSTATE, k=PDF.k),)
assert frags == expected
frags = merge_fragments(tuple(FPDF()._parse_chars("\\****BOLD**\\**", True)))
expected = (
Fragment("**", GSTATE, k=PDF.k),
Fragment("BOLD", GSTATE_B, k=PDF.k),
Fragment("**", GSTATE, k=PDF.k),
)
assert frags == expected
frags = merge_fragments(tuple(FPDF()._parse_chars("* **BOLD**", True)))
expected = (
Fragment("* ", GSTATE, k=PDF.k),
Fragment("BOLD", GSTATE_B, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_line_of_markers_escaped():
frags = merge_fragments(tuple(FPDF()._parse_chars("\\****BOLD**", True)))
expected = (
Fragment("**", GSTATE, k=PDF.k),
Fragment("BOLD", GSTATE_B, k=PDF.k),
)
assert frags == expected
frags = merge_fragments(tuple(FPDF()._parse_chars("*\\***BOLD**", True)))
expected = (Fragment("****BOLD", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_parse_newline_after_markdown_link(): # issue 916
text = "[fpdf2](https://py-pdf.github.io/fpdf2/)\nGo visit it!"
frags = merge_fragments(tuple(FPDF()._parse_chars(text, True)))
gstate_link = GSTATE.copy()
gstate_link.underline = True
expected = (
Fragment(
"fpdf2",
gstate_link,
k=PDF.k,
link="https://py-pdf.github.io/fpdf2/",
),
Fragment("\nGo visit it!", GSTATE, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_trailing_escape():
frags = merge_fragments(tuple(FPDF()._parse_chars("trailing \\\\", True)))
expected = (Fragment("trailing \\\\", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_parse_escape_non_marker():
frags = merge_fragments(tuple(FPDF()._parse_chars(r"\a", True)))
expected = (Fragment(r"\a", GSTATE, k=PDF.k),)
assert frags == expected
def test_markdown_parse_escape_before_marker_odd_even():
frags = tuple(FPDF()._parse_chars("\\\\**bold**", True))
expected = (
Fragment("\\\\", GSTATE, k=PDF.k),
Fragment("bold", GSTATE_B, k=PDF.k),
)
assert frags == expected
frags = tuple(FPDF()._parse_chars("\\**bold**", True))
expected = (
Fragment("**", GSTATE, k=PDF.k),
Fragment("bold", GSTATE, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_marker_adjacency():
frags = merge_fragments(tuple(FPDF()._parse_chars("a***b", True)))
expected = (Fragment("a***b", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(FPDF()._parse_chars("**bold***", True))
expected = (Fragment("bold***", GSTATE_B, k=PDF.k),)
assert frags == expected
def test_markdown_parse_across_newline():
frags = tuple(FPDF()._parse_chars("**bold\nstill**", True))
expected = (Fragment("bold\nstill", GSTATE_B, k=PDF.k),)
assert frags == expected
def test_markdown_parse_nested_combinations():
frags = tuple(FPDF()._parse_chars("**bold --under--**", True))
gstate_bu = GSTATE.copy()
gstate_bu.font_style = "B"
gstate_bu.underline = True
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("under", gstate_bu, k=PDF.k),
)
assert frags == expected
frags = tuple(FPDF()._parse_chars("~~strike __ital__~~", True))
gstate_si = GSTATE_S.copy()
gstate_si.font_style = "I"
expected = (
Fragment("strike ", GSTATE_S, k=PDF.k),
Fragment("ital", gstate_si, k=PDF.k),
)
assert frags == expected
def test_markdown_parse_link_variations():
frags = tuple(FPDF()._parse_chars("[go](2)", True))
assert len(frags) == 1
assert "".join(frags[0].characters) == "go"
assert isinstance(frags[0].link, int)
assert frags[0].graphics_state.underline is True
frags = tuple(FPDF()._parse_chars("[**bold**](https://example.com)", True))
assert len(frags) == 1
assert "".join(frags[0].characters) == "**bold**"
assert frags[0].graphics_state.underline is True
assert frags[0].graphics_state.font_style == ""
assert frags[0].link == "https://example.com"
frags = tuple(FPDF()._parse_chars("[x](url)**y**", True))
assert len(frags) == 2
assert "".join(frags[0].characters) == "x"
assert frags[0].graphics_state.underline is True
assert frags[0].link == "url"
assert "".join(frags[1].characters) == "y"
assert frags[1].graphics_state.font_style == "B"
frags = tuple(FPDF()._parse_chars("\\[x](url)", True))
expected = (
Fragment("\\", GSTATE, k=PDF.k),
Fragment("x", GSTATE_U, k=PDF.k, link="url"),
)
assert frags == expected
assert frags[1].link == "url"
|
