-
Notifications
You must be signed in to change notification settings - Fork 0
/
dictionary.py
368 lines (328 loc) · 13.1 KB
/
dictionary.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
#!/usr/bin/env python3
"""dictionary.py
This file contains the implementation of the Dictionary class.
"""
from entry import Entry
from headword import Headword
from output_helper import is_above
import logging
import re
def convert_to_string(cell):
"""convert the value of a cell to stripped text, but leave it
None if it is None.
"""
if cell:
return str(cell).strip()
else:
return None
def parse(text):
"""parse analyses the text for (Western) and (Eastern) variants and
splits the text into potentially three values. These values are
returned as a list of Headwords.
"""
result = []
if not text:
return result
# This regular expression searches for an optional comma (which we are
# not interested in as it can only start at the beginning of the string
# or directly after a pair of matching brackets). We then find
# non-bracket characters, followed by non-bracket characters within a
# pair of brackets. In case of a match the first element of the tuple
# is the word and the second element of the tuple is the label within
# the brackets. Note that this ignores everything following the last
# pair of brackets in case of a match.
hws = text.split(';')
for hw in hws:
marker = Headword.Marker_type.NONE
text = hw.strip()
east = re.match("(.*)\(Eastern\)", hw, re.I)
west = re.match("(.*)\(Western\)", hw, re.I)
if east:
text = east[1].strip()
marker = Headword.Marker_type.EAST
elif west:
text = west[1].strip()
marker = Headword.Marker_type.WEST
result.append(Headword(text, marker))
return result
def get_latex_header():
"""get_latex_header returns a string with a LaTeX header for the
dictionary.
"""
return """\\documentclass[10pt]{extarticle}
\\usepackage{array}
\\usepackage[backend=biber,style=authoryear,maxbibnames=99]{biblatex}
\\defbibheading{subbibliography}{}
\\addbibresource{publications.bib}
\\usepackage{booktabs}
\\usepackage[dvips=false,pdftex=false,vtex=false]{geometry}
\\setlength{\columnseprule}{0.4pt}
\\geometry{
a4paper,
left=23mm,
right=10mm,
top=15mm,
bottom=15mm,
includehead,
twoside
}
\\usepackage{fancyhdr}
\\newcommand*\\nowtitle{}
\\fancyhead[L]{\\rightmark} % Top left header
\\fancyhead[R]{\\leftmark} % Top right header
\\fancyhead[C]{\\textbf{\\nowtitle \\thepage}} % Top center header
\\fancyfoot[L]{} % Bottom left footer
\\fancyfoot[R]{} % Bottom right footer
\\fancyfoot[C]{} % Bottom center footer
\\renewcommand{\\headrulewidth}{0.4pt} % Rule under the header
\\renewcommand{\\footrulewidth}{0pt} % Rule under the footer
\\addtolength{\\textheight}{\\headsep}
\\setlength{\\headsep}{0pt} % Separator between header and text
\\pagestyle{fancy} % Use the custom headers and footers throughout the document
% headervalue, headword, pos, IPA, meaning, parentheticals
\\usepackage{graphicx}
\\usepackage{linguex}
\\usepackage{multicol}
\\usepackage{tipa}
\\newcommand{\\entry}[6]{#2\\markboth{#1}{#1} #3 #4 #5 #6}
\\setlength{\parindent}{0cm}
\\setlength{\parskip}{0mm}
\\usepackage[final,hidelinks]{hyperref}
\\urlstyle{rm}
\\newcommand{\\nocontentsline}[3]{}
\\newcommand{\\tocless}[2]{\\bgroup\\let\\addcontentsline=\\nocontentsline#1{#2}\\egroup}
\\begin{document}
\\include{intro}
\\begin{multicols}{2}
"""
def get_latex_footer():
"""get_latex_footer returns a string with a LaTeX footer for the
dictionary.
"""
return """\\end{multicols}
\\end{document}
"""
def skip_sort_words(word, i):
l = len(word)
if i + 7 < l and word[i:i + 7] == "iemand ": #
return (i + 7, True)
if i + 7 < l and word[i:i + 7] == "(wees) ": #
return (i + 7, True)
if i + 5 < l and word[i:i + 5] == "(be) ": #
return (i + 5, True)
if i + 5 < l and word[i:i + 5] == "iets ": #
return (i + 5, True)
if i + 5 < l and word[i:i + 5] == "wees ": #
return (i + 5, True)
if i + 4 < l and word[i:i + 4] == "die ": #
return (i + 4, True)
if i + 4 < l and word[i:i + 4] == "the ": #
return (i + 4, True)
if i + 3 < l and word[i:i + 3] == "be ": #
return (i + 3, True)
if i + 3 < l and word[i:i + 3] == "'n ": #
return (i + 3, True)
if i + 3 < l and word[i:i + 3] == "om ": #
return (i + 3, True)
if i + 3 < l and word[i:i + 3] == "te ": #
return (i + 3, True)
if i + 2 < l and word[i:i + 2] == "a ": #
return (i + 2, True)
# skip -, `, space, and LAST QUARTER MOON (9790) if present
if i < l and word[i] in "- `'(" + chr(9790):
return (i + 1, True)
return (i, False)
#! #!
sort_in = "āâēêëīîōôūû"
sort_in += "ʘǀǁ"
sort_in += "!" + chr(451)
sort_in += "ǂ"
sort_out = "aaeeeiioouu"
sort_out += chr(ord("z")+1) + chr(ord("z")+2) + chr(ord("z")+3)
sort_out += chr(ord("z")+4) + chr(ord("z")+4)
sort_out += chr(ord("z")+5)
def clean_sort(element):
"""clean_sort simplifies entries (element) such that they can be
ordered properly together.
"""
# grab the string representation and lowercase
clean_element = str(element).lower()
i_word = 0
l_word = len(clean_element)
# skip words
(i_word, skipped) = skip_sort_words(clean_element, i_word)
while skipped:
(i_word, skipped) = skip_sort_words(clean_element, i_word)
clean_element = clean_element[i_word:]
# clean letters
trans_map = clean_element.maketrans(sort_in, sort_out)
clean_element = clean_element.translate(trans_map)
result = ""
for i in clean_element:
if not is_above(ord(i)):
result += i
return result
def entry_sort(entry, element, lang):
"""entry_sort provides a string that can be used to sort within
entries of the same clean_sort.
"""
result = []
# grab the string representation and lowercase
el = str(element).lower()
i_word = 0
l_word = len(el)
# skip words
(i_word, skipped) = skip_sort_words(el, i_word)
while skipped:
(i_word, skipped) = skip_sort_words(el, i_word)
# first the cleaned headword
result.append(el[i_word:])
# next the POS
result.append(Entry.pos2text(entry.pos))
# next the other headwords
result.append(", ".join(map(str, [hw for hw in entry.headwords[lang] if hw != element])))
# next the skipped initial part
result.append(el[:i_word])
return " @ ".join(result)
class Dictionary:
"""The Dictionary class stores all information for the dictionary. It
checks whether all the required information is present.
"""
def __init__(self):
# Entries contains the list of dictionary entries (instances of the
# Entry class). The position in this list is used in the mappings
# (below).
self.entries = []
# The lang_map maps a headword to the entry (index) in the
# entries variable. The sort_map keeps the simplified word
# (used for sorting) as keys, mapping to the entries (indices)
# in the entries variable as well as the original word (so a
# tuple of index and original word).
self.lang_map = {}
self.sort_map = {}
for lang in Entry.Lang_type:
self.lang_map[lang] = {}
self.sort_map[lang] = {}
def check_add_map(self, element, lang, index, line_nr):
"""Check_add_map checks whether the element is empty and if not, it adds
it to the mapping, storing the index. It uses the name for warnings in
case elements are already present. line_nr is the number of the current
line.
"""
if element != None:
# Add entry to lang_map
if element in self.lang_map[lang]:
lines = []
for el in self.lang_map[lang][element]:
lines.append(self.entries[el].line_nr)
logging.warning("Duplicate value on line " + str(line_nr) + " " + Entry.lang2text(lang) + ": " + str(element) + " also found on line(s) " + ", ".join(lines))
self.lang_map[lang][element].append(index)
else: # Set initial value
self.lang_map[lang][element] = [index]
# Add entry to sort_map, first find word to order on
sort_element = clean_sort(element)
if sort_element in self.sort_map[lang]:
self.sort_map[lang][sort_element].append((index, element))
else: # Set initial value
self.sort_map[lang][sort_element] = [(index, element)]
def insert(self, n_uu, pos, ipa, nama, afrikaans, afr_loc, english, par_nama, par_afrikaans, par_english, audio_word, audio_sentence, line_nr):
"""Create and add the entry to the entries list. Len(self.entries)
provides the index of the new entry. Parse the language
and IPA fields.
"""
# Create headwords
hws = {}
hws[Entry.Lang_type.NUU] = parse(n_uu)
if ipa:
hws[Entry.Lang_type.IPA] = parse(ipa)
if nama:
hws[Entry.Lang_type.NAMA] = parse(nama)
if afrikaans:
hws[Entry.Lang_type.AFRIKAANS] = parse(afrikaans)
if afr_loc:
hws[Entry.Lang_type.AFR_LOC] = parse(afr_loc)
if english:
hws[Entry.Lang_type.ENGLISH] = parse(english)
parentheticals = {}
if par_nama:
parentheticals[Entry.Lang_type.NAMA] = par_nama
if par_afrikaans:
parentheticals[Entry.Lang_type.AFRIKAANS] = par_afrikaans
if par_english:
parentheticals[Entry.Lang_type.ENGLISH] = par_english
if not pos:
pos = ""
logging.warning("Missing POS on line " + str(line_nr))
# Add information to entries
self.entries.append(Entry(hws, pos, parentheticals, audio_word, audio_sentence, line_nr))
new_index = len(self.entries) - 1 # Get index which is length - 1
# Insert information in self.lang_map
for lang in hws:
for hw in hws[lang]:
self.check_add_map(hw, lang, new_index, line_nr)
def insert_line(self, line, line_nr):
"""Insert_line adds a line from the spreadsheet into the dictionary
(self). It parses the Orthography 1 and IPA fields as there may be
eastern or western variants in there.
"""
# Convert to string (if needed) and remove any whitespace at beginning
# or end.
n_uu = convert_to_string(line["Orthography 1"])
ipa = convert_to_string(line["IPA"])
pos = convert_to_string(line["Part of Speech, English"])
nama = convert_to_string(line["Nama Feedback"])
par_nama = convert_to_string(line["Nama Parentheticals"])
afrikaans = convert_to_string(line["Afrikaans community feedback HEADWORD"])
afr_loc = convert_to_string(line["Afrikaans community feedback Local Variety "])
par_afrikaans = convert_to_string(line["Afrik Parentheticals"])
english = convert_to_string(line["English"])
par_english = convert_to_string(line["Parentheticals, English"])
audio_word = convert_to_string(line["Dictionary Recording (target word only)"])
audio_sentence = convert_to_string(line["Recordings (target word in sentence)"])
self.insert(n_uu, pos, ipa, nama, afrikaans, afr_loc, english, par_nama, par_afrikaans, par_english, audio_word, audio_sentence, line_nr)
def __str__(self):
"""__str__ provides printable output.
"""
result = "Dictionary(Entries:\n"
for i in self.entries:
result += " " + str(i) + "\n"
result += ")"
return result
def get_portal(self):
"""get_portal returns a string of the dictionary information
in the format that can be used for the dictionary portal.
"""
result = ""
for i in self.entries:
result += i.get_portal()
return result
def get_lang_latex(self, lang):
"""get_lang_latex returns a string with the LaTeX lemmas
sorted according to mapping.
"""
result = "{\\hfill\\\\\\Large\\textbf{" + Entry.lang2latex_long(lang) + "}}\\\\\n"
result += "\\phantomsection%\n"
result += "\\addcontentsline{toc}{section}{" + Entry.lang2latex_long(lang) + "}%\n"
result += "\\renewcommand*\\nowtitle{" + Entry.lang2latex_long(lang) + " }%\n"
for element in sorted(self.sort_map[lang]):
for values in sorted(self.sort_map[lang][element], key = lambda x: entry_sort(self.entries[x[0]], x[1], lang)):
index = values[0] # index in entries
word = values[1] # actual, original word
result += self.entries[index].get_latex(word, lang)
result += "\\newpage\n"
return result
def get_latex(self):
"""get_latex returns a string containing the dictionary
information.
"""
result = get_latex_header()
### N|uu
result += self.get_lang_latex(Entry.Lang_type.NUU)
### Nama
result += self.get_lang_latex(Entry.Lang_type.NAMA)
### Afrikaans
result += self.get_lang_latex(Entry.Lang_type.AFRIKAANS)
### English
result += self.get_lang_latex(Entry.Lang_type.ENGLISH)
result += get_latex_footer()
return result