4 USAGE: translations-status.py BUILDSCRIPT-DIR LOCALEDIR
6 This script must be run from Documentation/
8 Reads template files translations.template.html.in
9 and for each LANG in LANGUAGES LANG/translations.template.html.in
10 Writes translations.html.in and for each LANG in LANGUAGES
11 translations.LANG.html.in
12 Writes out/translations-status.txt
13 Updates word counts in TRANSLATION
25 sys.stderr.write (str + '\n')
27 progress ("translations-status.py")
31 # load gettext messages catalogs
32 translation = langdefs.translation
35 language_re = re.compile (r'^@documentlanguage (.+)', re.M)
36 comments_re = re.compile (r'^@ignore\n(.|\n)*?\n@end ignore$|@c .*?$', re.M)
37 space_re = re.compile (r'\s+', re.M)
38 lilypond_re = re.compile (r'@lilypond({.*?}|(.|\n)*?\n@end lilypond$)', re.M)
39 node_re = re.compile ('^@node .*?$', re.M)
40 title_re = re.compile ('^@(top|chapter|(?:sub){0,2}section|' + \
41 '(?:unnumbered|appendix)(?:(?:sub){0,2}sec)?) (.*?)$', re.M)
42 include_re = re.compile ('^@include (.*?)$', re.M)
44 translators_re = re.compile (r'^@c\s+Translators\s*:\s*(.*?)$', re.M | re.I)
45 checkers_re = re.compile (r'^@c\s+Translation\s*checkers\s*:\s*(.*?)$',
47 status_re = re.compile (r'^@c\s+Translation\s*status\s*:\s*(.*?)$', re.M | re.I)
48 post_gdp_re = re.compile ('post.GDP', re.I)
49 untranslated_node_str = '@untranslated'
50 skeleton_str = '-- SKELETON FILE --'
52 section_titles_string = _doc ('Section titles')
53 last_updated_string = _doc (' <p><i>Last updated %s</i></p>\n')
54 detailed_status_heads = [_doc ('Translators'), _doc ('Translation checkers'),
55 _doc ('Translated'), _doc ('Up to date'),
58 'not translated': {'color':'d0f0f8', 'short':_doc ('no'), 'abbr':'NT',
59 'long':_doc ('not translated')},
60 'partially translated': {'color':'dfef77',
61 'short':_doc ('partially (%(p)d %%)'),
63 'long':_doc ('partially translated (%(p)d %%)')},
64 'fully translated': {'color':'1fff1f', 'short':_doc ('yes'), 'abbr':'FT',
65 'long': _doc ('translated')},
66 'up to date': {'short':_doc ('yes'), 'long':_doc ('up to date'),
67 'abbr':'100%%', 'vague':_doc ('up to date')},
68 'outdated': {'short':_doc ('partially'), 'abbr':'%(p)d%%',
69 'vague':_doc ('partially up to date')},
70 'N/A': {'short':_doc ('N/A'), 'abbr':'N/A', 'color':'d587ff', 'vague':''},
71 'pre-GDP':_doc ('pre-GDP'),
72 'post-GDP':_doc ('post-GDP')
76 # (Unumbered/Numbered/Lettered, level)
78 'unnumbered': ('u', 1),
79 'unnumberedsec': ('u', 2),
80 'unnumberedsubsec': ('u', 3),
83 'subsection': ('n', 3),
87 appendix_number_trans = string.maketrans ('@ABCDEFGHIJKLMNOPQRSTUVWXY',
88 'ABCDEFGHIJKLMNOPQRSTUVWXYZ')
90 class SectionNumber (object):
92 self.__data = [[0,'u']]
94 def __increase_last_index (self):
95 type = self.__data[-1][1]
97 self.__data[-1][0] = \
98 self.__data[-1][0].translate (appendix_number_trans)
100 self.__data[-1][0] += 1
103 if self.__data[-1][1] == 'u':
105 return '.'.join ([str (i[0]) for i in self.__data if i[1] != 'u']) + ' '
107 def increase (self, (type, level)):
109 self.__data = [[0,'u']]
110 while level + 1 < len (self.__data):
112 if level + 1 > len (self.__data):
113 self.__data.append ([0, type])
115 self.__data[-1][0] = '@'
116 if type == self.__data[-1][1]:
117 self.__increase_last_index ()
119 self.__data[-1] = ([0, type])
121 self.__data[-1][0] = 'A'
123 self.__data[-1][0] = 1
124 return self.format ()
127 def percentage_color (percent):
130 c = [hex (int (3 * p * b + (1 - 3 * p) * a))[2:]
131 for (a, b) in [(0xff, 0xff), (0x5c, 0xa6), (0x5c, 0x4c)]]
133 c = [hex (int ((3 * p - 1) * b + (2 - 3 * p) * a))[2:]
134 for (a, b) in [(0xff, 0xff), (0xa6, 0xff), (0x4c, 0x3d)]]
136 c = [hex (int ((3 * p - 2) * b + 3 * (1 - p) * a))[2:]
137 for (a, b) in [(0xff, 0x1f), (0xff, 0xff), (0x3d, 0x1f)]]
141 def update_word_count (text, filename, word_count):
142 return re.sub (r'(?m)^(\d+) *' + filename,
143 str (word_count).ljust (6) + filename,
146 po_msgid_re = re.compile (r'^msgid "(.*?)"(?:\n"(.*?)")*', re.M)
148 def po_word_count (po_content):
149 s = ' '.join ([''.join (t) for t in po_msgid_re.findall (po_content)])
150 return len (space_re.split (s))
152 sgml_tag_re = re.compile (r'<.*?>', re.S)
154 def sgml_word_count (sgml_doc):
155 s = sgml_tag_re.sub ('', sgml_doc)
156 return len (space_re.split (s))
158 def tely_word_count (tely_doc):
160 Calculate word count of a Texinfo document node by node.
162 Take string tely_doc as an argument.
163 Return a list of integers.
165 Texinfo comments and @lilypond blocks are not included in word counts.
167 tely_doc = comments_re.sub ('', tely_doc)
168 tely_doc = lilypond_re.sub ('', tely_doc)
169 nodes = node_re.split (tely_doc)
170 return [len (space_re.split (n)) for n in nodes]
173 class TelyDocument (object):
174 def __init__ (self, filename):
175 self.filename = filename
176 self.contents = open (filename).read ()
178 ## record title and sectionning level of first Texinfo section
179 m = title_re.search (self.contents)
181 self.title = m.group (2)
182 self.level = texi_level [m.group (1)]
184 self.title = 'Untitled'
185 self.level = ('u', 1)
187 m = language_re.search (self.contents)
189 self.language = m.group (1)
191 included_files = [os.path.join (os.path.dirname (filename), t)
192 for t in include_re.findall (self.contents)]
193 self.included_files = [p for p in included_files if os.path.exists (p)]
195 def print_title (self, section_number):
196 return section_number.increase (self.level) + self.title
199 class TranslatedTelyDocument (TelyDocument):
200 def __init__ (self, filename, masterdocument, parent_translation=None):
201 TelyDocument.__init__ (self, filename)
203 self.masterdocument = masterdocument
204 if not hasattr (self, 'language') \
205 and hasattr (parent_translation, 'language'):
206 self.language = parent_translation.language
207 if hasattr (self, 'language'):
208 self.translation = translation[self.language]
210 self.translation = lambda x: x
211 self.title = self.translation (self.title)
213 ## record authoring information
214 m = translators_re.search (self.contents)
216 self.translators = [n.strip () for n in m.group (1).split (',')]
218 self.translators = parent_translation.translators
219 m = checkers_re.search (self.contents)
221 self.checkers = [n.strip () for n in m.group (1).split (',')]
222 elif isinstance (parent_translation, TranslatedTelyDocument):
223 self.checkers = parent_translation.checkers
227 ## check whether translation is pre- or post-GDP
228 m = status_re.search (self.contents)
230 self.post_gdp = bool (post_gdp_re.search (m.group (1)))
232 self.post_gdp = False
234 ## record which parts (nodes) of the file are actually translated
235 self.partially_translated = not skeleton_str in self.contents
236 nodes = node_re.split (self.contents)
237 self.translated_nodes = [not untranslated_node_str in n for n in nodes]
239 ## calculate translation percentage
240 master_total_word_count = sum (masterdocument.word_count)
241 translation_word_count = \
242 sum ([masterdocument.word_count[k] * self.translated_nodes[k]
243 for k in range (min (len (masterdocument.word_count),
244 len (self.translated_nodes)))])
245 self.translation_percentage = \
246 100 * translation_word_count / master_total_word_count
248 ## calculate how much the file is outdated
249 (diff_string, error) = \
250 buildlib.check_translated_doc (masterdocument.filename, self.filename, self.contents)
252 sys.stderr.write ('warning: %s: %s' % (self.filename, error))
253 self.uptodate_percentage = None
255 diff = diff_string.splitlines ()
256 insertions = sum ([len (l) - 1 for l in diff
257 if l.startswith ('+')
258 and not l.startswith ('+++')])
259 deletions = sum ([len (l) - 1 for l in diff
260 if l.startswith ('-')
261 and not l.startswith ('---')])
262 outdateness_percentage = 50.0 * (deletions + insertions) / \
263 (masterdocument.size + 0.5 * (deletions - insertions))
264 self.uptodate_percentage = 100 - int (outdateness_percentage)
265 if self.uptodate_percentage > 100:
267 progress ("%s: strange uptodateness percentage %d %%, \
268 setting to %d %%" % (self.filename, self.uptodate_percentage, alternative))
269 self.uptodate_percentage = alternative
270 elif self.uptodate_percentage < 1:
272 progress ("%s: strange uptodateness percentage %d %%, \
273 setting to %d %%" % (self.filename, self.uptodate_percentage, alternative))
274 self.uptodate_percentage = alternative
276 def completeness (self, formats=['long'], translated=False):
278 translation = self.translation
280 translation = lambda x: x
282 if isinstance (formats, str):
284 p = self.translation_percentage
286 status = 'not translated'
288 status = 'fully translated'
290 status = 'partially translated'
291 return dict ([(f, translation (format_table[status][f]) % locals())
294 def uptodateness (self, formats=['long'], translated=False):
296 translation = self.translation
298 translation = lambda x: x
300 if isinstance (formats, str):
302 p = self.uptodate_percentage
306 status = 'up to date'
311 if f == 'color' and p != None:
312 l['color'] = percentage_color (p)
314 l[f] = translation (format_table[status][f]) % locals ()
317 def gdp_status (self):
319 return self.translation (format_table['post-GDP'])
321 return self.translation (format_table['pre-GDP'])
323 def short_html_status (self):
325 if self.partially_translated:
326 s += '<br>\n '.join (self.translators) + '<br>\n'
329 '<br>\n '.join (self.checkers) + '</small><br>\n'
331 c = self.completeness (['color', 'long'])
332 s += ' <span style="background-color: #%(color)s">\
333 %(long)s</span><br>\n' % c
335 if self.partially_translated:
336 u = self.uptodateness (['vague', 'color'])
337 s += ' <span style="background-color: #%(color)s">\
338 %(vague)s</span><br>\n' % u
343 def text_status (self):
344 s = self.completeness ('abbr')['abbr'] + ' '
346 if self.partially_translated:
347 s += self.uptodateness ('abbr')['abbr'] + ' '
350 def html_status (self, numbering=SectionNumber ()):
351 if self.title == 'Untitled':
354 if self.level[1] == 0: # if self is a master document
355 s = '''<table align="center" border="2">
357 <th>%s</th>''' % self.print_title (numbering)
358 s += ''.join ([' <th>%s</th>\n' % self.translation (h)
359 for h in detailed_status_heads])
361 s += ' <tr align="left">\n <td>%s<br>(%d)</td>\n' \
362 % (self.translation (section_titles_string),
363 sum (self.masterdocument.word_count))
366 s = ' <tr align="left">\n <td>%s<br>(%d)</td>\n' \
367 % (self.print_title (numbering),
368 sum (self.masterdocument.word_count))
370 if self.partially_translated:
371 s += ' <td>' + '<br>\n '.join (self.translators) + '</td>\n'
372 s += ' <td>' + '<br>\n '.join (self.checkers) + '</td>\n'
374 s += ' <td></td>\n' * 2
376 c = self.completeness (['color', 'short'], translated=True)
377 s += ' <td><span style="background-color: #%(color)s">\
378 %(short)s</span></td>\n' % {'color': c['color'],
381 if self.partially_translated:
382 u = self.uptodateness (['short', 'color'], translated=True)
383 s += ' <td><span style="background-color: #%(color)s">\
384 %(short)s</span></td>\n' % {'color': u['color'],
389 s += ' <td>' + self.gdp_status () + '</td>\n </tr>\n'
390 s += ''.join ([i.translations[self.language].html_status (numbering)
391 for i in self.masterdocument.includes
392 if self.language in i.translations])
394 if self.level[1] == 0: # if self is a master document
395 s += '</table>\n<p></p>\n'
398 class MasterTelyDocument (TelyDocument):
401 parent_translations=dict ([(lang, None)
402 for lang in langdefs.LANGDICT])):
403 TelyDocument.__init__ (self, filename)
404 self.size = len (self.contents)
405 self.word_count = tely_word_count (self.contents)
406 translations = dict ([(lang, os.path.join (lang, filename))
407 for lang in langdefs.LANGDICT])
408 self.translations = \
410 TranslatedTelyDocument (translations[lang],
411 self, parent_translations.get (lang)))
412 for lang in langdefs.LANGDICT
413 if os.path.exists (translations[lang])])
414 if self.translations:
415 self.includes = [MasterTelyDocument (f, self.translations)
416 for f in self.included_files]
420 def update_word_counts (self, s):
421 s = update_word_count (s, self.filename, sum (self.word_count))
422 for i in self.includes:
423 s = i.update_word_counts (s)
426 def html_status (self, numbering=SectionNumber ()):
427 if self.title == 'Untitled' or not self.translations:
429 if self.level[1] == 0: # if self is a master document
430 s = '''<table align="center" border="2">
432 <th>%s</th>''' % self.print_title (numbering)
433 s += ''.join ([' <th>%s</th>\n' % l for l in self.translations])
435 s += ' <tr align="left">\n <td>Section titles<br>(%d)</td>\n' \
436 % sum (self.word_count)
438 else: # if self is an included file
439 s = ' <tr align="left">\n <td>%s<br>(%d)</td>\n' \
440 % (self.print_title (numbering), sum (self.word_count))
442 s += ''.join ([t.short_html_status ()
443 for t in self.translations.values ()])
445 s += ''.join ([i.html_status (numbering) for i in self.includes])
447 if self.level[1] == 0: # if self is a master document
448 s += '</table>\n<p></p>\n'
451 def text_status (self, numbering=SectionNumber (), colspec=[48,12]):
452 if self.title == 'Untitled' or not self.translations:
456 if self.level[1] == 0: # if self is a master document
457 s += (self.print_title (numbering) + ' ').ljust (colspec[0])
458 s += ''.join (['%s'.ljust (colspec[1]) % l
459 for l in self.translations])
461 s += ('Section titles (%d)' % \
462 sum (self.word_count)).ljust (colspec[0])
466 % (self.print_title (numbering), sum (self.word_count))
467 s = s.ljust (colspec[0])
469 s += ''.join ([t.text_status ().ljust(colspec[1])
470 for t in self.translations.values ()])
472 s += ''.join ([i.text_status (numbering) for i in self.includes])
474 if self.level[1] == 0:
479 update_category_word_counts_re = re.compile (r'(?ms)^-(\d+)-(.*?\n)\d+ *total')
481 counts_re = re.compile (r'(?m)^(\d+) ')
483 def update_category_word_counts_sub (m):
484 return '-' + m.group (1) + '-' + m.group (2) + \
486 for c in counts_re.findall (m.group (2))])).ljust (6) + \
490 progress ("Reading documents...")
493 buildlib.read_pipe ("find -maxdepth 2 -name '*.tely'")[0].splitlines ()
495 master_docs = [MasterTelyDocument (os.path.normpath (filename))
496 for filename in tely_files]
497 master_docs = [doc for doc in master_docs if doc.translations]
499 main_status_page = open ('translations.template.html.in').read ()
501 enabled_languages = [l for l in langdefs.LANGDICT
502 if langdefs.LANGDICT[l].enabled
504 lang_status_pages = \
505 dict ([(l, open (os.path.join (l, 'translations.template.html.in')). read ())
506 for l in enabled_languages])
508 progress ("Generating status pages...")
510 date_time = buildlib.read_pipe ('LANG= date -u')[0]
512 main_status_html = last_updated_string % date_time
513 main_status_html += '\n'.join ([doc.html_status () for doc in master_docs])
515 html_re = re.compile ('<html>', re.I)
516 end_body_re = re.compile ('</body>', re.I)
518 html_header = '''<html>
519 <!-- This page is automatically generated by translation-status.py from
520 translations.template.html.in; DO NOT EDIT !-->'''
522 main_status_page = html_re.sub (html_header, main_status_page)
524 main_status_page = end_body_re.sub (main_status_html + '\n</body>',
527 open ('translations.html.in', 'w').write (main_status_page)
529 for l in enabled_languages:
530 date_time = buildlib.read_pipe ('LANG=%s date -u' % l)[0]
531 lang_status_pages[l] = translation[l] (last_updated_string) % date_time + lang_status_pages[l]
532 lang_status_page = html_re.sub (html_header, lang_status_pages[l])
533 html_status = '\n'.join ([doc.translations[l].html_status ()
534 for doc in master_docs
535 if l in doc.translations])
536 lang_status_page = end_body_re.sub (html_status + '\n</body>',
538 open (os.path.join (l, 'translations.html.in'), 'w').write (lang_status_page)
540 main_status_txt = '''Documentation translations status
543 FT = fully translated
547 main_status_txt += '\n'.join ([doc.text_status () for doc in master_docs])
549 status_txt_file = 'out/translations-status.txt'
550 progress ("Writing %s..." % status_txt_file)
551 open (status_txt_file, 'w').write (main_status_txt)
553 translation_instructions_file = 'TRANSLATION'
554 progress ("Updating %s..." % translation_instructions_file)
555 translation_instructions = open (translation_instructions_file).read ()
557 for doc in master_docs:
558 translation_instructions = doc.update_word_counts (translation_instructions)
560 for html_file in re.findall (r'(?m)^\d+ *(\S+?\.html\S*?)(?: |$)',
561 translation_instructions):
562 word_count = sgml_word_count (open (html_file).read ())
563 translation_instructions = update_word_count (translation_instructions,
567 for po_file in re.findall (r'(?m)^\d+ *(\S+?\.po\S*?)(?: |$)',
568 translation_instructions):
569 word_count = po_word_count (open (po_file).read ())
570 translation_instructions = update_word_count (translation_instructions,
574 translation_instructions = \
575 update_category_word_counts_re.sub (update_category_word_counts_sub,
576 translation_instructions)
578 open (translation_instructions_file, 'w').write (translation_instructions)