-
Notifications
You must be signed in to change notification settings - Fork 0
/
json_mine_xml.py
567 lines (513 loc) · 16.7 KB
/
json_mine_xml.py
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
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
import PyPDF2
import re
import matplotlib.pyplot as plt
from PyPDF2 import PdfFileWriter, PdfFileReader, PdfFileMerger
import StringIO
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import letter
import subprocess
import os
import sys
#filename = sys.argv[1]
filename = ""
#"0302007"
#"0303124"
#"0304011"
#"9602063"
#"1605.02019"
#"9610131"
directory = "loading_dock/json_latexml/"
class ME():
me_latex = [] #Exact latex syntax
me_refnum_list = {}
#me_list = [] #Me string form to match with PDFBOX
me_prev_text = {} #Text before ME (~25 characters)
me_post_text = {} #Text after ME (~25 characters)
me_with_ss_scripts = {}
xml_text = "" #XLM text in seq order (same as pdf) without ME
xml_full_text = ""
xml_lines = [] #XLM line data
me_ref_list = {} #ME bib cite refs
me_cite_num = {} #ME number ref
figure_cite_num = {} #Figure number ref
ref_recovery_location = {} #location to swap reference key with value
ref_rec_loc_class = {} #some cite class change the [] to ()
title_count = 1
#Some class types change how things are represented in the PDF
REF_CITE_CLASS = {
"ltx_citemacro_cite" : ["[to(", "]to)"]
}
#Python is dumb so yeah
number_list = ["0","1","2","3","4","5","6","7","8","9"]
def format_xml_math_space():
#Make sure the <Math mode= is on new line >>>> :( AIDS
outfile = open(directory + filename + "_formated.xml", "w")
with open(directory + filename ) as fn:
for line in fn:
multi_me_check = [m.start() for m in re.finditer("<Math mode=", line)]
if(len(multi_me_check) > 1):
last_pos = 0
new_line = line.split("<Math mode=")
i = 1
outfile.write(new_line[0])
while(i < len(new_line)):
outfile.write("\n<Math mode=" + new_line[i])
i = i + 1
else:
outfile.write(line)
outfile.close()
def format_xml_ref_space():
#Make sure the <Math mode= is on new line >>>> :( AIDS
outfile = open(directory + filename + "_formated_final.xml", "w")
with open(directory + filename + "_formated.xml") as fn:
comment_flag = 0
for line in fn:
#print("line", line)
if(comment_flag == 1 and re.search("-->", line)):
comment_flag = 0
new_line = line.split("-->")
#print("OI", new_line)
line = new_line[1]
if(re.search("<!--", line)):
if(re.search("-->", line)):
print("")
else:
#print("wtf", line)
comment_flag = 1
continue
if(comment_flag == 1):
continue
multi_me_check = [m.start() for m in re.finditer("<ref labelref=", line)]
if(len(multi_me_check) > 1):
last_pos = 0
new_line = line.split("<ref labelref=")
i = 1
outfile.write(new_line[0])
while(i < len(new_line)):
outfile.write("\n<ref labelref=" + new_line[i])
i = i + 1
else:
outfile.write(line)
outfile.close()
os.remove(directory + filename + "_formated.xml")
#Newcite fix could have bugs in future... Need to watch it close
def ref_recovery():
for ref_loc in ME.ref_recovery_location:
data = ME.xml_lines[ref_loc]
if(ME.ref_recovery_location[ref_loc] == "ERROR"):
#fix \newcite errors, figure out correct ref since it is unknown
for ref in ME.me_ref_list:
gues_ref = "\\\\newcite" + ref
if(re.search(gues_ref, data)):
data = data.split("newcite")
data[1] = data[1].split(ref)
data = data[0][0:len(data[0])-1] + ME.me_ref_list[ref] + data[1][1]
ME.xml_lines[ref_loc] = data
else:
data = data.split(ME.ref_recovery_location[ref_loc])
if(ref_loc in ME.ref_rec_loc_class):
if(ME.ref_rec_loc_class[ref_loc] in REF_CITE_CLASS):
CLASS_RULE = REF_CITE_CLASS[ME.ref_rec_loc_class[ref_loc]]
i = 0
for rule in CLASS_RULE:
rule = rule.split("to")
if(i == 0):
try:
if(data[0][-1] == rule[0]):
data[0] = data[0][0:len(data[0])-1] + rule[1]
except:
print("RULE ERROR line 133")
else:
try:
if(len(data) == 1):
if(data[0][-1] == rule[0]):
data[0] = data[0][0:len(data[0])-1] + rule[1]
else:
if(data[1][0] == rule[0]):
data[1] = rule[1] + data[1][1:len(data[1])]
except:
print("RULE ERROR LINE 139")
i = i + 1
if(re.search(",", ME.ref_recovery_location[ref_loc])):
#More than one ref
multi_refs = ME.ref_recovery_location[ref_loc].split(",")
new_ref = ""
i = 0
for mref in multi_refs:
if(mref in ME.me_ref_list):
new_ref = new_ref + ME.me_ref_list[mref]
if(i+1 < len(multi_refs)):
new_ref = new_ref + ","
i = i + 1
if(len(data) == 1):
data = data[0] + new_ref
else:
data = data[0] + new_ref + data[1]
ME.xml_lines[ref_loc] = data
else:
if(ME.ref_recovery_location[ref_loc] in ME.me_ref_list):
if(len(data) == 1):
try:
data = data[0] + ME.me_ref_list[ME.ref_recovery_location[ref_loc]]
except:
data = data[0] + "[REF:ERROR]"
else:
try:
data = data[0] + ME.me_ref_list[ME.ref_recovery_location[ref_loc]] + data[1]
except:
data = data[0] + "[REF:ERROR]" + data[1]
ME.xml_lines[ref_loc] = data
ME.xml_text = ""
for line in ME.xml_lines:
if(isinstance(line,list)):
line = line[0]
ME.xml_text = ME.xml_text + line
def check_missmatch_sign(data):
#< only
le_flag = 0
ge_flag = 0
last_index = 0
i = 0
for char in data:
if(char == "<"):
if(le_flag == 1):
#double <
data = data[0:i-1] + ">" + data[i:len(data)]
i = i + 1
last_index = i
else:
le_flag = le_flag + 1
elif(char == ">"):
if(le_flag == 0):
#Problem add < to start
#print("oi1", data, i)
data = data[0:last_index] + "<" + data[last_index+1:len(data)]
#print("oi2", data)
i = i + 1
le_flag = 0
ge_flag = 0
last_index = i
elif(ge_flag == 1):
#double >>
data = data[0:i-1] + "<" + data[i:len(data)]
i = i + 1
last_index = i
else:
ge_flag = ge_flag + 1
if(le_flag == 1 and ge_flag == 1):
le_flag = 0
ge_flag = 0
last_index = i + 1
i = i + 1
if(le_flag == 1):
data = data + ">"
if(ge_flag == 1):
data = "<" + data
return data
def outfile_data():
#Write to out file
print("HERE_OUTFILE")
directory = filename + "_jsondata/"
if not os.path.exists(directory):
os.makedirs(directory)
out_file = open(filename + "_jsondata/" + filename + "_xmlmined.txt", "w")
out_file.write(ME.xml_text)
out_file.close()
out_file = open(filename + "_jsondata/" + filename + "_melist.txt", "w")
for me in ME.me_latex:
me = me + "\n"
out_file.write(me)
out_file.close()
out_file = open(filename + "_jsondata/" + filename + "_merefnumlist.txt", "w")
for meref in ME.me_refnum_list:
meref = ME.me_refnum_list[meref] +"," +str(meref) + "\n"
out_file.write(meref)
out_file.close()
def parse_latex_from_xml(filename):
count = 0
reference_flag = 0
key = 0
unique_me_cite_count = 0
unique_figure_cite_count = 0
me_count = 0
mathbranch_found = 0
toccation_found = 0
last_me_ref = ""
last_section_ref = ""
#Need to get ref key list first
with open(directory + filename + "_formated_final.xml") as fn:
for line in fn:
words = line
#print words
#print("\n\n\n\n")
#Math brank and XMtok repeat the ME in different format
#toccaption duplicates data in xml for figure captions
if("References" in words):
reference_flag = 1
if(reference_flag == 1):
#This block gets all references in the xml and their xml key
if(re.search("bibitem key", words)):
#Get ref key
bibref = words.split("key=\"")
bibref = bibref[1].split("\"")
key = bibref[0]
#Get ref name
if(re.search("<bibtag role=\"refnum\"", words)):
if(re.search("</ERROR>", words)):
nameref = words.split("</ERROR>")
nameref = nameref[1].split("</bibtag>")
nameref = nameref[0]
else:
nameref = words.split("bibtag role=\"refnum\">")
nameref = nameref[1].split("</bibtag>")
nameref = nameref[0]
if(re.search("et al.", nameref)):
#These refs in xml are missing () after et al.
nameref = nameref.split("et al.")
nameref = nameref[0] + "etal.(" + nameref[1] + ")"
nameref = nameref.replace(" ", "")
ME.me_ref_list[key] = nameref
continue
if(re.search("<toccaption", line)):
toccation_found = 1
if(re.search("</toccaption>", line)):
toccation_found = 0
words = words.split("</toccaption>")
if(len(words) < 1):
continue
words = words[1]
elif(re.search("</toccaption>", line)):
toccation_found = 0
words = words.split("</toccaption>")
if(len(words) < 1):
continue
words = words[1]
if(toccation_found == 1):
continue
if(re.search("<MathBranch", line)):
mathbranch_found = 1
if(re.search("</MathBranch>", line)):
mathbranch_found = 0
words = words.split("</MathBranch>")
if(len(words) < 1):
continue
words = words[1]
elif(re.search("</MathBranch>", line)):
mathbranch_found = 0
words = words.split("</MathBranch>")
if(len(words) < 1):
continue
words = words[1]
if(mathbranch_found == 1):
continue
if(re.search("(?<=<XMath>)(.*)(?=<\/XMath>)", words)):
tmp_words = words
tmp_words = tmp_words.split("<XMath>")
new_words = tmp_words[0]
tmp_words = tmp_words[1].split("</XMath>")
new_words = new_words + tmp_words[1]
words = new_words
elif(re.search("XMTok", words)):
continue
if(re.search("(?<=xml:id=\")(.*)(?=\")", words)):
#p = re.compile("(?<=xml:id=\")(.*)(?=\" )")
#replacement = p.findall(words)[0]
tmp_words = words
tmp_words = tmp_words.split("xml:id=\"")
new_words = tmp_words[0]
tmp_words = tmp_words[1].split("\"")
i = 1
while(i < len(tmp_words)):
new_words = new_words + tmp_words[i]
if(i <= len(tmp_words)-2):
new_words = new_words + "\""
i = i + 1
#print("replacement", replacement)
#words = words.replace(replacement, "")
words = new_words
if(re.search("ref labelref", words)):
#Found ME equation ref number
cite_key = words.split("ref labelref=\"")
cite_key = cite_key[1].split("\"")
cite_key = cite_key[0]
#print("cite_key", cite_key, words)
#print ME.me_cite_num
words = words.split("<ref l")
if(re.search("fig", cite_key)):
#Figure num instead of ME
if(cite_key not in ME.figure_cite_num):
unique_figure_cite_count = unique_figure_cite_count + 1
ME.figure_cite_num[cite_key] = unique_figure_cite_count
words = words[0] + str(unique_figure_cite_count) + "<ref l" + words[1]
else:
words = words[0] + str(ME.figure_cite_num[cite_key]) + "<ref l" + words[1]
elif(cite_key not in ME.me_cite_num):
#print("WTF", words, cite_key)
unique_me_cite_count = unique_me_cite_count + 1
ME.me_cite_num[cite_key] = unique_me_cite_count
#print str(ME.me_cite_num[cite_key])
words = words[0] + str(unique_me_cite_count) + "<ref l" + words[1]
elif(cite_key in ME.me_cite_num):
words = words[0] + str(ME.me_cite_num[cite_key]) + "<ref l" + words[1]
if(re.search("bibref", words)):
words = words.split("<bibref bibrefs=\"")
if(len(words) > 1):
bib_key = words[1].split("\" separator")
print bib_key
words = words[0] + bib_key[0] + "<" + words[1]
ME.ref_recovery_location[count] = bib_key[0]
if(re.search("class=\"", words)):
cite_class = words.split("class=\"")
cite_class = cite_class[1].split("\">")
cite_class = cite_class[0]
ME.ref_rec_loc_class[count] = cite_class
try:
if(re.search("\\\\newcite", words)):
#Some refs fail correct format in XML and appear with \newcite</ERROR>
#Has two \\ for some reason?!?@!? AIDS
ME.ref_recovery_location[count] = "ERROR"
except:
print("RE SEARCH FAIL LINE 399")
#Check if ME has (#) ref, should be placed after ME
try:
if(re.search("<equation frefnum=", words)):
#print("WTFF", words)
me_ref_num = words.split("<equation frefnum=\"")
me_ref_num = me_ref_num[1].split("\"")
last_me_ref = me_ref_num[0]
#print("meref_num", last_me_ref)
if(re.search("labels=\"", words)):
check_label = words.split("labels=\"")
check_label = check_label[1].split("\"")
check_label = check_label[0]
if(check_label not in ME.me_cite_num):
ME.me_cite_num[check_label] = last_me_ref
unique_me_cite_count = unique_me_cite_count + 1
ME.me_refnum_list[me_count] = last_me_ref
elif(re.search("<equation refnum=", words)):
me_ref_num = words.split("<equation refnum=\"")
me_ref_num = me_ref_num[1].split("\"")
last_me_ref = me_ref_num[0]
if(re.search("labels=\"", words)):
check_label = words.split("labels=\"")
check_label = check_label[1].split("\"")
check_label = check_label[0]
if(check_label not in ME.me_cite_num):
ME.me_cite_num[check_label] = last_me_ref
unique_me_cite_count = unique_me_cite_count + 1
if(last_me_ref[0] != "("):
last_me_ref = "(" + last_me_ref + ")"
ME.me_refnum_list[me_count] = last_me_ref
elif(re.search("<equation ", words)):
if(re.search("refnum=\"", words)):
me_ref_num = words.split("refnum=\"")
me_ref_num = me_ref_num[1].split("\"")
last_me_ref = me_ref_num[0]
if(re.search("labels=\"", words)):
check_label = words.split("labels=\"")
check_label = check_label[1].split("\"")
check_label = check_label[0]
if(check_label not in ME.me_cite_num):
ME.me_cite_num[check_label] = last_me_ref
unique_me_cite_count = unique_me_cite_count + 1
if(last_me_ref[0] != "("):
last_me_ref = "(" + last_me_ref + ")"
ME.me_refnum_list[me_count] = last_me_ref
except:
print("RE SEARCH FAIL LINE 409-451")
#print last_me_ref
try:
if(re.search("section refnum=\"", words)):
section_id = words.split("section refnum=\"")
section_id = section_id[1].split("\"")
last_section_ref = section_id[0]
except:
print("RE SEARCH FAIL LINE 457")
#Grab all ME in tex=""
try:
if(re.search("tex=", words)):
#[m.start() for m in re.finditer(pdf_char, ME.me_post_text[index])]
multi_me_check = [m.start() for m in re.finditer("tex=\"", words)]
#if(len(multi_me_check) > 1):
# print("o shit", words)
latex = words.split("tex=\"")
latex = latex[1].split("\"")
latex[0] = latex[0].replace("\"", "")
if(re.search("^{}", latex[0])):
#Not a ME, just odd format for titles
print("AYE")
else:
#print("MELOC", latex[0])
ME.me_latex.append(latex[0])
#print("ME", latex[0])
#Replace ME with [ME#]
me_split = words.split("tex=\"")
#[m.start() for m in re.finditer("ref labelref=\"", line)]
#check for xml:id and text, sometimes they are swapped
me_split_two = me_split[1].split("\"")
#wtf = me_split_two[1].split(">")
#if(len(wtf) == 1):
# me_split_two[1] = me_split_two[1] + ">"
i = 2
while(i < len(me_split_two)):
me_split_two[1] = me_split_two[1] + "\""+ me_split_two[i]
i = i + 1
#print("WTF REF NUM", last_me_ref)
new_words = me_split[0] + ">[ME#]" + last_me_ref + "< \"" + me_split_two[1]
#print("new words", new_words)
#print("last_me_ref", last_me_ref)
last_me_ref = ""
words = new_words
#print("words", words)
me_count = me_count + 1
except:
print("RE SEARCH FAIL 466")
if(reference_flag == 0):
words = check_missmatch_sign(words)
title_flag = 0
try:
if(re.search("<title>", words)):
#Check to make sure number is before it
title_flag = 1
except:
print("RE SEARCH FAIL 510")
try:
words = re.sub("<[^>]+>", "", words)
#words = words.replace(" ", "")
words = words.replace("\r", "")
words = words.replace("\n", "")
if(title_flag == 1):
id_size = len(last_section_ref)
curr_id = words[0:id_size]
#print("exptected ID", curr_id)
#print("actual ID", last_section_ref)
#print("for words:= ", words)
#Need special condition for <I Introduction>
if(curr_id != last_section_ref):
words = last_section_ref + words
elif(last_section_ref == "I" and words[1:12] == "ntroduction"):
words = last_section_ref + words
#Fix for sub sections and etc
#if(words[0] not in number_list):
# words = str(ME.title_count) + words
ME.title_count = ME.title_count + 1
except:
print("UNKOWN BULLSHIT at 516")
#print words
#print("\n\n")
if(len(words) == 1):
ME.xml_lines.append(words[0])
ME.xml_text = ME.xml_text + words[0]
else:
ME.xml_lines.append(words)
ME.xml_text = ME.xml_text + words
count = count + 1
#print ME.xml_text
#print ME.ref_rec_loc_class
#print ME.me_ref_list
ref_recovery()
outfile_data()
for filename in os.listdir(directory):
format_xml_math_space()
format_xml_ref_space()
parse_latex_from_xml(filename)