-
Notifications
You must be signed in to change notification settings - Fork 0
/
pre.py
362 lines (271 loc) · 11.5 KB
/
pre.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
''' texify.py converts "chord lines" to injected \chord{} LaTeX tags '''
import os
import re
import glob
import errno
import numpy as np
import argparse
def chord_positions(chordline):
''' Returns a list of chords and their respective positions in line. '''
chords = chordline.split()
start = 0
positions = []
for c in chords:
start = chordline.index(c, start)
positions.append(start)
start += len(c)
return chords, positions
def mini_tex_escape(line):
''' Handles minimal TeX escaping (F#, ...). Complicate as needed. '''
line = line.replace('#', '\#')
return line
def get_all_files_from(directory):
owd = os.getcwd()
os.chdir(directory)
files = []
for file in glob.glob("*.txt"):
files.append(file)
os.chdir(owd)
return files
def inject_line(line, chords, positions):
''' Injects chords onto their positions into line. '''
injected_line = ""
last = 0
for i in range(len(chords)):
if re.match("\(.*\)", chords[i]):
injected_line += chords[i]
else:
# try to fix chords after the last word in each line (WIP)
if len(line) >= positions[i]:
injected_line += line[last:positions[i]]
else:
if last < len(line):
injected_line += line[last:positions[i]]
N = 4 - (len(line) - last) + 2
else:
N = 4
#print(N)
injected_line += "\phantom{"+ "N"*N +"}"
injected_line += "\chord{" + chords[i] + "}"
last = positions[i]
injected_line += line[last:]
return mini_tex_escape(injected_line)
def inline_chord_line(line):
chords = line.split()
for i in range(len(chords)):
if re.match("\(.*\)", chords[i]):
pass
else:
chords[i] = "\inlinechord{" + chords[i] + "}"
return mini_tex_escape('~~'.join(chords))
def texify_song(file_location):
''' Converts file with structure:
C G D
lyrics lyrics lyrics lyrics lyrics
into
\chord{C}lyrics lyr\chord{G}ics lyr\chord{C}ics lyrics lyrics
assuming whitespace as chord-separator and always even/odd separation
for chords/lyrics.
'''
with open(file_location, 'r', encoding="utf-8") as f:
lines = f.read().splitlines()
chordlines = lines[::2]
textlines = lines[1::2]
for i in range(len(chordlines)):
chords, positions = chord_positions(chordlines[i])
injected_line = inject_line(textlines[i], chords, positions)
print(injected_line + "\\\\")
def strumming_pattern(text):
bars = text.split()
formated = []
for bar in bars:
n = len(bar) // 2
formated.append('\\begin{tabular}{{@{} ' + ' '.join(['c@{}c' for i in range(n)]) + ' @{}}}')
arrows = ['$\\downarrow$' if t == 'd' else \
'$\\uparrow$' if t == 'u' else \
'$\\times$' if t == 'x' else \
'$\\downarrowcrossed$' if t == 'y' else \
'$\\uparrowcrossed$' if t == 'z' else \
'' for t in bar]
formated.append(' & '.join(arrows) + '\\\\')
numbers = [str(i//2 + 1) if i%2 == 0 else '-' for i in range(2*n)]
formated.append(' & '.join(numbers) + '\\\\')
formated.append('\\end{tabular}')
return '\n'.join(formated)
def parse_song_info(data):
song_info = {'Title': [], 'By': [], 'Capo': [], 'Strumming': {}, 'Note': []}
song_info['Strumming']['Note'] = []
song_info['Strumming']['Pattern'] = []
for line in data.splitlines():
m = re.match(r'Title: (.*)', line)
if m:
song_info['Title'] = m.group(1)
m = re.match(r'By: (.*)', line)
if m:
song_info['By'] = m.group(1)
m = re.match(r'Capo: (.*)', line)
if m:
song_info['Capo'] = m.group(1)
m = re.match(r'Strumming: ([duxyz\-\s]*)(\(.*\))?', line)
if m:
#strum = strumming_pattern(m.group(1))
strum = tikz_strumming(m.group(1))
song_info['Strumming']['Note'].append(m.group(2))
song_info['Strumming']['Pattern'].append(strum)
m = re.match(r'Note: (.*)', line)
if m:
song_info['Note'] = m.group(1)
formated = '\\addcontentsline{{toc}}{{section}}{{{Title}}}\n'.format(**song_info)
formated += '{{\\Large\\bfseries {Title}}}~{{\\large\\bfseries\\itshape ({By})}}'.format(**song_info)
if args.capo or args.note or args.strumming:
formated += '\\\\[3ex]\n'
if song_info['Capo'] and args.capo:
formated += '\\textbf{{Capo}}: {Capo}\\\\[1ex]\n'.format(**song_info)
if song_info['Strumming'] and args.strumming:
for note, pattern in zip(song_info['Strumming']['Note'], song_info['Strumming']['Pattern']):
if note:
note = ' ' + note
else:
note = ''
formated += '\\textbf{{Strumming}}{}:\\\\[1ex]\n{}\\\\[1ex]\n'.format(note, pattern)
if song_info['Note'] and args.note:
formated += '\\textbf{{Note}}: {Note}\\\\[1ex]\n'.format(**song_info)
# formated text always ends with something like '\\[3ex]\n' - this creates
# an extra space after the last line -- delete in (i know it's a bad practice) :-)
formated = re.sub(r'\\\\\[[0-9]ex\]\n$', '\n\n', formated)
return formated
def split_song(file_location, save_folder):
''' Handles anotated txt file. Allowed tags (and file structure):
[Info]
Title:
By:
Capo:
Strumming:
If the tag ends with `*`, it contains only chords:
e.g. [Intro*], [Outro*], [Ending*], ...
If the tag ends with `&`, it contains only text:
e.g. [Verse&], [Chorus&], ...
Otherwise, it contains chords and text lins:
e.g. [Bridge], [Pre-Chorus], [Interlude]...
'''
with open(file_location, 'r', encoding="utf-8") as f:
txt = f.read()
with open(save_folder + '/' + file_location.split("/")[-1] + '.tex', 'w', encoding="utf-8") as f:
song_parts = re.split(r'(\[[\w\-\*\&]+\])\s*\n', txt)
if song_parts[0] == '':
song_parts.pop(0)
tags = song_parts[::2]
data = song_parts[1::2]
for j, tag in enumerate(tags):
tags[j] = tag.strip()
used_chords = ''
for j, (tag, dat) in enumerate(zip(tags, data)):
if tag.lower() == '[info]':
pass
elif re.match(r'\[[\w\-]+\*\]', tag.lower()):
used_chords += dat.strip() + ' '
elif re.match(r'\[[\w\-]+\]', tag.lower()):
lines = [s for s in dat.splitlines() if s]
chordlines = lines[::2]
used_chords += ' ' + ' '.join(chordlines) + ' '
elif re.match(r'\[[\w\-]+\&\]', tag.lower()):
pass
else:
print("Unidentified tag {}".format(tag))
raise
# remove all characters except for 'A-Z', 'a-z', '0-9', '/', '#', '()', and whitespace
used_chords = re.sub(r'([^A-Za-z0-9/#\(\)\s]+)',' ',used_chords)
used_chords = re.sub(r'(\(.*\))',' ',used_chords)
# LaTeX does not like '#' character to be used in macros
# -- better replace it and deal with it in LaTeX
used_chords = re.sub('#','+',used_chords)
used_chords = ', '.join(set(used_chords.split()))
# print(used_chords)
for j, (tag, dat) in enumerate(zip(tags, data)):
tag_string = re.sub(r'[\[\]\&\*]','',tag.title())
if tag.lower() == '[info]':
f.write(parse_song_info(dat) + '\n' + '\\bigskip\n')
f.write('\n\\chordlist{{{}}}\\\\\n'.format(used_chords))
elif re.match(r'\[[\w\-]+\*\]', tag.lower()):
if args.compact:
f.write('\n\\textbf{{{}}}:~'.format(tag_string) + '{{\\sffamily {}}}\n'.format(inline_chord_line(dat.strip())) + '\\\\\n')
else:
f.write('\n\\textbf{{{}}}:\\\\[1ex]\n'.format(tag_string) + '{{\\sffamily {}}}\n'.format(inline_chord_line(dat.strip())) + '\\\\\n')
elif re.match(r'\[[\w\-]+\&?\]', tag.lower()):
lines = [s for s in dat.splitlines() if s]
# print(tag)
if re.match(r'\[[\w\-]+\]', tag.lower()):
chordlines = lines[::2]
textlines = lines[1::2]
parsed = ''
for i in range(len(chordlines)):
chords, positions = chord_positions(chordlines[i])
# print(chords)
injected_line = inject_line(textlines[i], chords, positions)
# print(injected_line + "\\\\")
parsed += injected_line + '\\\\\n'
elif re.match(r'\[[\w\-]+\&\]', tag.lower()):
parsed = '\\\\\n'.join(lines) + '\\\\\n'
else:
print("Unidentified tag {}".format(tag))
raise
parsed = parsed.replace(' ','~')
if args.compact:
f.write('\n\\textbf{{{}}}:~'.format(tag_string))
else:
f.write('\n\\textbf{{{}}}:\\\\[1ex]\n'.format(tag_string))
f.write('{{\\sffamily {}}}\n'.format(parsed))
def make_sure_path_exists(path):
try:
os.makedirs(path)
except OSError as exception:
if exception.errno != errno.EEXIST:
raise
def tikz_strumming(line):
out = ''
for l in line.split():
out += tikz_strumming_single_pattern(l)
return out
def tikz_strumming_single_pattern(line):
out = r'\begin{tikzpicture}'
out += r'\coordinate (A0) at (0,0.25);' \
+ r'\coordinate (A1) at (0,0);' \
+ r'\coordinate (A2) at (0.5,0);' \
+ r'\coordinate (A3) at (0.5,0.25);'
line = line.strip()
n = 2
for j, a in enumerate([line[i:i+n] for i in range(0, len(line), n)]):
out += tikz_strumming_part(j, a)
out += r'\end{tikzpicture}'
return out
def tikz_strumming_part(j, code):
out = ''
for i in np.arange(4):
out += r'\coordinate (A%d) at ($(A%d) + (1,0)$);' % (i,i)
out += r'\path [draw] (A0)--(A1)--(A2)--(A3);'
out += r'\path [draw] ($ (A1) + (0,0.05) $)--($ (A2) + (0,0.05) $);'
out += r'\node [above=0.0 of A0] {\footnotesize \color{gray} %d};' %(j+1)
out += r'\node [above=0.0 of A3] {\footnotesize \color{gray} \&};'
out += tikz_strumming_resolve_code('(A0)', code[0])
out += tikz_strumming_resolve_code('(A3)', code[1])
return out
def tikz_strumming_resolve_code(node, code):
out = ''
if code in 'dy':
out += r'\draw [thick,<-] ($%s + (0,0.55)$) -- ++(0,0.5);' % (node)
if code in 'uz':
out += r'\draw [thick,->] ($%s + (0,0.55)$) -- ++(0,0.5);' % (node)
if code in 'xyz':
out += r'\coordinate (C) at ($%s + (0,0.55) + (0,0.25)$);' % (node)
out += r'\draw (C) node[cross=0.1cm,rotate=0] {};'
return out
parser = argparse.ArgumentParser(description='Preprocessing...')
parser.add_argument('--capo', action='store_true')
parser.add_argument('--compact', action='store_true')
parser.add_argument('--note', action='store_true')
parser.add_argument('--strumming', action='store_true')
args = parser.parse_args()
make_sure_path_exists('songs_tex')
for song in get_all_files_from('songs_txt'):
print("Preprocessing song {}".format(song))
split_song('songs_txt/'+song, 'songs_tex')