X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=scripts%2Fauxiliar%2Ftranslations-status.py;h=221746360be79e305bf270fa13584f9fd1f6bf24;hb=HEAD;hp=c17e9532f7d98afc5c8440723a3d3eb002fee5a9;hpb=00322ca2a6ce40fa689ae65be0e6f8c8267e26ad;p=lilypond.git diff --git a/scripts/auxiliar/translations-status.py b/scripts/auxiliar/translations-status.py index c17e9532f7..221746360b 100755 --- a/scripts/auxiliar/translations-status.py +++ b/scripts/auxiliar/translations-status.py @@ -10,6 +10,19 @@ USAGE: cd Documentation && translations-status.py Update word counts in: contributor/doc-translation-list.itexi + +TODO: + * using markup = TexiMarkup (), html tables (columns) + are evenly spaced and bit too wide. This can + be fixed by using + @multitable @columnfractions 0 0 0 0 0 0 0 0, + but with that, PDF and info output get borked. + * in info and PDF, columns have too little separation + * using markup = HTMLMarkup (), we get nice + + popups -- do we want that with texi output? -- how? + or possibly links to the git archive? + ''' import sys @@ -44,22 +57,20 @@ comments_re = re.compile (r'^@ignore\n(.|\n)*?\n@end ignore$|@c .*?$', re.M) space_re = re.compile (r'\s+', re.M) lilypond_re = re.compile (r'@lilypond({.*?}|(.|\n)*?\n@end lilypond$)', re.M) node_re = re.compile ('^@node .*?$', re.M) -title_re = re.compile ('^@(top|chapter|(?:sub){0,2}section|' + \ -'(?:unnumbered|appendix)(?:(?:sub){0,2}sec)?) (.*?)$', re.M) +title_re = re.compile ('^@(settitle|chapter|top|(?:sub){0,2}section|' + '(?:unnumbered|appendix)(?:(?:sub){0,2}sec)?) (.*?)$', re.M) include_re = re.compile ('^@include (.*?)$', re.M) # allow multiple lines -translators_re = re.compile (r'^@c\s+[tT]ranslators?\s*:\s*(.*?)$', re.M | re.I) -# FIXME: use revision: (or proofreading:?) -checkers_re = re.compile (r'^@c\s+Translation\s*checkers\s*:\s*(.*?)$', - re.M | re.I) -status_re = re.compile (r'^@c\s+Translation\s*status\s*:\s*(.*?)$', re.M | re.I) +translators_re = re.compile (r'^@c[ ]+[Tt]ranslators?[ ]*:[ ]*(.*?)$', re.M) +checkers_re = re.compile (r'^@c[ ]+[Tt]ranslation[ ]*[Cc]heckers?[ ]*:[ ]*(.*?)$', re.M) +status_re = re.compile (r'^@c[ ]+[Tt]ranslation[ ]*[Ss]tatus[ ]*:[ ]*(.*?)$', re.M) post_gdp_re = re.compile ('post.GDP', re.I) untranslated_node_str = '@untranslated' skeleton_str = '-- SKELETON FILE --' section_titles_string = _doc ('Section titles') -last_updated_string = _doc ('

Last updated %s

\n') +last_updated_string = _doc ('Last updated %s') detailed_status_heads = [_doc ('Translators'), _doc ('Translation checkers'), _doc ('Translated'), _doc ('Up to date'), _doc ('Other info')] @@ -179,39 +190,155 @@ def tely_word_count (tely_doc): nodes = node_re.split (tely_doc) return [len (space_re.split (n)) for n in nodes] +class HTMLMarkup (object): + texi_header = '''@c -*- coding: utf-8; mode: texinfo; -*- +@c This file was generated by translation-status.py -- DO NOT EDIT! +@ignore + Translation of GIT committish: 0 +@end ignore + +''' + texi_footer = ''' +''' + def texi (self, string): + return (self.texi_header + + ''' +@ifnothtml +Translation status currently only available in HTML. +@end ifnothtml +''' + + string + + self.texi_footer) + def entity (self, name, string='', attributes=[]): + attr_list = ''.join ([' %s="%s"' % x for x in attributes]) + return '<%(name)s%(attr_list)s>%(string)s' % locals () + def paragraph (self, string=''): + return self.entity ('p', string) + def table (self, string): + return self.entity ('table', string, [('align', 'center'), ('border', '2')]) + def row (self, string, attributes=[]): + return self.entity ('tr', string, attributes) + headrow = row + def headcell (self, string, attributes=[]): + return self.entity ('th', string, attributes) + def cell (self, string='', attributes=[]): + return self.entity ('td', string, attributes) + def newline (self, attributes=[]): + return self.entity ('br', '', attributes)[:-5] + def span (self, string, attributes=[]): + return self.entity ('span', string, attributes) + def small (self, string, attributes=[]): + return self.entity ('small', string, attributes) + def emph (self, string, attributes=[]): + return self.entity ('em', string, attributes) + +class TexiMarkup (HTMLMarkup): + def texi (self, string): + return (self.texi_header + + self.html (''' + +''') + + self.columnfraction_disaster (self.itemtab_disaster (string)) + + self.texi_footer) + def itemtab_disaster (self, string): + return string.replace ('''item \n@tab ''', '''item +''') + def columnfraction_disaster (self, string): + if False: + # nice trick for html-only + return string.replace ('@multitable', '@multitable @columnfractions 0 0 0 0 0 0 0 0 0 0') + tables = re.findall ('(?s)(@multitable)(.*?)(@item)', string) + for t in tables: + columns = len (re.findall ('(?s)(\n@tab)', t[1])) + 1 + columnfractions = '@columnfractions ' + (' ' + str (1.0/columns)) * columns + string = string.replace ('@multitable\n', + '@multitable %(columnfractions)s\n' % locals (), 1) + return string + def entity (self, name, string='', attributes=[]): + return ''' +@%(name)s +%(string)s +@end %(name)s''' % locals () + def paragraph (self, string=''): + return ''' +%(string)s''' % locals () + def table (self, string): + # Ugh, makeinfo is fine without @columnfractions + # but texi2html 1.82 barfs: `empty multicolumn' + return (self.entity ('multitable', string)) + def headrow (self, string, attributes=[]): + return ''' +@headitem ''' + string + def row (self, string, attributes=[]): + return ''' +@item ''' + string + def cell (self, string='', attributes=[]): + return ''' +@tab ''' + string + headcell = cell + def newline (self): + return ''' +@* +''' + def html (self, string): + return self.entity ('ifhtml', self.entity ('html', string)) + def nothtml (self, string): + return self.entity ('ifnothtml', string) + def span (self, string, attributes=[]): + return (self.html (HTMLMarkup ().span (string, attributes)) + + self.nothtml (string)) + def small (self, string, attributes=[]): + return (self.html (HTMLMarkup ().small (string, attributes)) + + self.nothtml (string)) + def command (self, name, string): + return '@%(name)s{%(string)s}' % locals () + def emph (self, string, attributes=[]): + return self.command ('emph', string) class TelyDocument (object): def __init__ (self, filename): self.filename = filename - self.contents = open (filename).read () - self.top = os.path.splitext (filename)[1] in ['.tely', '.texi'] + self.contents = 'GIT committish: 0' + if os.path.exists (filename): + self.contents = open (filename).read () ## record title and sectionning level of first Texinfo section self.sectioning = 'unnumbered' self.title = 'Untitled' m = title_re.search (self.contents) if m: self.sectioning = m.group (1) - if self.sectioning == 'top': - self.sectioning = 'unnumbered' self.title = m.group (2) - self.level = texi_level [self.sectioning] + if not hasattr (self, 'language'): + self.language = '' m = language_re.search (self.contents) if m: self.language = m.group (1) - included_files = [os.path.join (os.path.dirname (filename), t) + dir = os.path.dirname (filename).split ('/')[0] + if len (dir) == 2: + dir += '/' + else: + dir = '' + included_files = [dir + t for t in include_re.findall (self.contents)] self.included_files = [p for p in included_files if os.path.exists (p)] + def get_level (self): + return texi_level [self.sectioning] + def print_title (self, section_number): + if not hasattr (self, 'level'): + self.level = self.get_level () return section_number.increase (self.level) + self.title class TranslatedTelyDocument (TelyDocument): def __init__ (self, filename, masterdocument, parent_translation=None): TelyDocument.__init__ (self, filename) - self.masterdocument = masterdocument if not hasattr (self, 'language'): self.language = '' @@ -230,18 +357,22 @@ class TranslatedTelyDocument (TelyDocument): self.title = self.translation (self.title) ## record authoring information - self.translators = [] + self.translators = [''] if parent_translation: - self.translators = parent_translation.__dict__.get ('translators', []) + self.translators = parent_translation.__dict__.get ('translators', ['']) m = translators_re.findall (self.contents) if m: self.translators = [n.strip () for n in reduce (operator.add, [n.split (',') for n in m])] - if (not self.translators + if self.language != self.filename[:2]: + print 'Barf:', self.filename + barf + if (not isinstance (self, UntranslatedTelyDocument) + and (not self.translators or not self.translators[0]) and not 'macros.itexi' in self.filename): - error ('%s: no translator name found, \nplease \ -specify at least one in the master file as a line containing\n\ -@c Translators: FirstName1 LastName1, FirstName2 LastName2' % self.filename) + error (self.filename + ''': error: no translator name found + please specify one ore more lines in the master file + @c Translator: FirstName LastName[, FirstName LastName]..''') self.checkers = [] m = checkers_re.findall (self.contents) if m: @@ -299,6 +430,9 @@ setting to %d %%" % (self.filename, self.uptodate_percentage, alternative)) setting to %d %%" % (self.filename, self.uptodate_percentage, alternative)) self.uptodate_percentage = alternative + def get_level (self): + return texi_level ['top'] + def completeness (self, formats=['long'], translated=False): if translated: translation = self.translation @@ -346,85 +480,98 @@ setting to %d %%" % (self.filename, self.uptodate_percentage, alternative)) else: return self.translation (format_table['pre-GDP']) - def short_texi_status (self): - s = ' ' + def short_texi_status (self, markup): + s = '' if self.partially_translated: - s += '
\n '.join (self.translators) + '
\n' + s += markup.newline ().join (self.translators + ['']) if self.checkers: - s += ' ' + \ - '
\n '.join (self.checkers) + '
\n' - + s += markup.newline ().join ([markup.small (x) for x in self.checkers + ['']]) c = self.completeness (['color', 'long']) - s += ' \ -%(long)s
\n' % c - + s += markup.span ('%(long)s' % c, [('style', 'background-color: #%(color)s' % c)]) + s += markup.newline () if self.partially_translated: u = self.uptodateness (['vague', 'color']) - s += ' \ -%(vague)s
\n' % u - - s += ' \n' - return s + s += markup.span ('%(vague)s' % u, [('style', 'background-color: #%(color)s' % u)]) + return markup.cell (s, [('title', filename)]) def text_status (self): s = self.completeness ('abbr')['abbr'] + ' ' - if self.partially_translated: s += self.uptodateness ('abbr')['abbr'] + ' ' return s - def texi_status (self, numbering=SectionNumber ()): - if self.title == 'Untitled': - return '' - - if self.top: - s = ''' - - ''' % self.print_title (numbering) - s += ''.join ([' \n' % self.translation (h) - for h in detailed_status_heads]) - s += ' \n' - s += ' \n \n' \ - % (self.translation (section_titles_string), - sum (self.masterdocument.word_count)) - - else: - s = ''' ''' % self.__dict__ - s += ' \n \n' \ - % (self.print_title (numbering), - sum (self.masterdocument.word_count)) - + def texi_status (self, markup, numbering=SectionNumber ()): + return (markup.table ( + markup.headrow ( + (markup.headcell (self.print_title (numbering)) + + ''.join ([markup.headcell (self.translation (h)) + for h in detailed_status_heads])), + [('align', 'center')]) + + markup.row ( + (markup.cell ((self.translation (section_titles_string) + + markup.newline () + + '%d' % sum (self.masterdocument.word_count)), + [('title',filename)]) + + self.texi_body (markup, numbering)), + [('align','left')]) + + self.texi_translations (markup, numbering)) + ) + markup.paragraph () + + def texi_body (self, markup, numbering): + return (self.texi_translators (markup) + + self.texi_completeness (markup) + + self.texi_uptodateness (markup) + + self.texi_gdp (markup)) + + def texi_translators (self, markup): if self.partially_translated: - s += ' \n' - s += ' \n' - else: - s += ' \n' * 2 + return (markup.cell (markup.newline ().join (self.translators)) + + markup.cell (markup.newline ().join (self.checkers))) + return markup.cell () + markup.cell () + def texi_completeness (self, markup): c = self.completeness (['color', 'short'], translated=True) - s += ' \n' % {'color': c['color'], - 'short': c['short']} + return markup.cell (markup.span (c['short'], + [('style', 'background-color: #' + c['color'])])) + def texi_uptodateness (self, markup): if self.partially_translated: u = self.uptodateness (['short', 'color'], translated=True) - s += ' \n' % {'color': u['color'], - 'short': u['short']} - else: - s += ' \n' - - s += ' \n \n' - s += ''.join ([i.translations[self.language].texi_status (numbering) - for i in self.masterdocument.includes - if self.language in i.translations]) + return markup.cell (markup.span (u['short'], + [('style', 'background-color: #' + u['color'])])) + return markup.cell () + + def texi_gdp (self, markup): + return markup.cell (self.gdp_status ()) + + def texi_translations (self, markup, numbering): + return ''.join ([i.translations[self.language].texi_status (markup, numbering) + for i in self.masterdocument.includes + if self.language in i.translations]) + +class IncludedTranslatedTelyDocument (TranslatedTelyDocument): + get_level = TelyDocument.get_level + def texi_status (self, markup, numbering=SectionNumber ()): + if self.title != 'Untitled': + return (markup.row ( + (markup.cell (( + self.print_title (numbering) + + markup.newline () + + '%d' % sum (self.masterdocument.word_count)), + [('title',filename)]) + + self.texi_body (markup, numbering)), + [('align','left')]) + + self.texi_translations (markup, numbering)) + return '' + +class UntranslatedTelyDocument (TranslatedTelyDocument): + def __init__ (self, filename, masterdocument, parent_translation=None): + if filename[2] == '/': + self.language = filename[:2] + TranslatedTelyDocument.__init__ (self, filename, masterdocument, parent_translation) - if self.top: - s += '
%s%s
%s
(%d)
%s
(%d)		' + '
\n '.join (self.translators) + '		' + '
\n '.join (self.checkers) + '		\ -%(short)s\ -%(short)s' + self.gdp_status () + '
\n

\n' - return s +class IncludedUntranslatedTelyDocument (UntranslatedTelyDocument, IncludedTranslatedTelyDocument): + get_level = TelyDocument.get_level class MasterTelyDocument (TelyDocument): def __init__ (self, @@ -432,28 +579,28 @@ class MasterTelyDocument (TelyDocument): parent_translations=dict ([(lang, None) for lang in langdefs.LANGDICT])): TelyDocument.__init__ (self, filename) - self.sectioning = 'top' - self.title = 'Untitled' - m = title_re.search (self.contents) - if m: - self.title = m.group (2) - self.level = texi_level [self.sectioning] - self.size = len (self.contents) self.word_count = tely_word_count (self.contents) - translations = dict ([(lang, os.path.join (lang, filename)) - for lang in langdefs.LANGDICT]) - self.translations = \ - dict ([(lang, - TranslatedTelyDocument (translations[lang], - self, parent_translations.get (lang))) - for lang in langdefs.LANGDICT - if os.path.exists (translations[lang])]) - if self.translations: - self.includes = [MasterTelyDocument (f, self.translations) - for f in self.included_files] - else: - self.includes = [] + self.translations = {} + self.includes = [] + if not self.language or self.language == 'en': + languages = [x for x in parent_translations.keys () if x != 'en'] + self.translations = dict ([x for x in + [(lang, self.translated_factory (os.path.join (lang, self.filename), + parent_translations.get (lang))) + for lang in languages] + if x[1]]) + if self.translations: + self.includes = [IncludedMasterTelyDocument (f, self.translations) + for f in self.included_files] + + def get_level (self): + return texi_level ['top'] + + def translated_factory (self, filename, parent): + if os.path.exists (filename): + return TranslatedTelyDocument (filename, self, parent) + return None def update_word_counts (self, s): s = update_word_count (s, self.filename, sum (self.word_count)) @@ -461,62 +608,73 @@ class MasterTelyDocument (TelyDocument): s = i.update_word_counts (s) return s - def texi_status (self, numbering=SectionNumber ()): - if self.title == 'Untitled' or not self.translations: - return '' - if self.top: - s = ''' - - ''' % self.print_title (numbering) - s += ''.join ([' \n' % l for l in self.translations]) - s += ' \n' - s += ' \n \n' \ - % sum (self.word_count) - - else: # if self is an included file - s = ''' ''' % self.__dict__ - s += ' \n \n' \ - % (self.print_title (numbering), sum (self.word_count)) - - s += ''.join ([t.short_texi_status () - for t in self.translations.values ()]) - s += ' \n' - s += ''.join ([i.texi_status (numbering) for i in self.includes]) - - if self.top: - s += '
%s%s
Section titles
(%d)
%s
(%d)
\n

\n' + def texi_status (self, markup, numbering=SectionNumber ()): + return markup.table ( + (markup.headrow ( + (markup.headcell (self.print_title (numbering)) + + ''.join ([markup.headcell (l) for l in sorted (self.translations.keys ())])), + [('align','center')]) + + markup.row ( + (markup.cell (('Section titles' + + markup.newline () + + '(%d)' % sum (self.word_count)), + [('title',filename)]) + + self.texi_body (markup, numbering)), + [('align','left')]) + + self.texi_includes (markup, numbering) + )) + markup.paragraph () + + def texi_includes (self, markup, numbering): + return ''.join ([i.texi_status (markup, numbering) for i in self.includes]) + + def texi_body (self, markup, numbering): + return ''.join ([self.translations[k].short_texi_status (markup) + for k in sorted (self.translations.keys ())]) + + def text_status (self, markup, numbering=SectionNumber (), colspec=[48,12]): + s = (self.print_title (numbering) + ' ').ljust (colspec[0]) + s += ''.join (['%s'.ljust (colspec[1]) % l + for l in sorted (self.translations.keys ())]) + s += '\n' + s += ('Section titles (%d)' % \ + sum (self.word_count)).ljust (colspec[0]) + s += self.text_body (markup, numbering, colspec) + s += '\n' return s - def text_status (self, numbering=SectionNumber (), colspec=[48,12]): - if self.title == 'Untitled' or not self.translations: - return '' - - s = '' - if self.top: - s += (self.print_title (numbering) + ' ').ljust (colspec[0]) - s += ''.join (['%s'.ljust (colspec[1]) % l - for l in self.translations]) - s += '\n' - s += ('Section titles (%d)' % \ - sum (self.word_count)).ljust (colspec[0]) - - else: - s = '%s (%d) ' \ - % (self.print_title (numbering), sum (self.word_count)) - s = s.ljust (colspec[0]) - - s += ''.join ([t.text_status ().ljust(colspec[1]) - for t in self.translations.values ()]) - s += '\n\n' - s += ''.join ([i.text_status (numbering) for i in self.includes]) - - if self.top: - s += '\n' - return s + def text_body (self, markup, numbering, colspec): + return (''.join ([self.translations[k].text_status ().ljust(colspec[1]) + for k in sorted (self.translations.keys ())]) + + '\n\n' + + ''.join ([i.text_status (markup, numbering) for i in self.includes])) + +class IncludedMasterTelyDocument (MasterTelyDocument): + get_level = TelyDocument.get_level + + def translated_factory (self, filename, parent): + if os.path.exists (filename): + return IncludedTranslatedTelyDocument (filename, self, parent) + return IncludedUntranslatedTelyDocument (filename, self, parent) + + def texi_status (self, markup, numbering=SectionNumber ()): + if self.title != 'Untitled': + return (markup.row ( + (markup.cell ((self.print_title (numbering) + + markup.newline () + + '(%d)' % sum (self.word_count)), + [('title',filename)]) + + self.texi_body (markup, numbering)), + [('align','left')]) + + self.texi_includes (markup, numbering)) + return '' + + def text_status (self, markup, numbering=SectionNumber (), colspec=[48,12]): + if self.title != 'Untitled': + return (self.print_title (numbering) + + '(%d)' % sum (self.word_count) + + self.text_body (markup, numbering, colspec) + ).ljust (colspec[0]) + return '' update_category_word_counts_re = re.compile (r'(?ms)^-(\d+)-(.*?\n)\d+ *total') @@ -549,35 +707,28 @@ progress ("Generating status pages...") date_time = buildlib.read_pipe ('LANG= date -u')[0] -main_status_body = last_updated_string % date_time -main_status_body += '\n'.join ([doc.texi_status () for doc in master_docs]) - -texi_header = '''@c -*- coding: utf-8; mode: texinfo; -*- -@c This file was generated by translation-status.py -- DO NOT EDIT! - -@ifnothtml -Translation status currently only available in HTML. -@end ifnothtml -@ifhtml -@html -''' - -texi_footer = ''' -@end html -@end ifhtml -''' +# TEXI output sort of works +# TODO: table border, td-titles :-) +# markup = HTMLMarkup () +#sys.stderr.write ('''translations-status.py:713: warning: using markup = HTMLMarkup (): HTML only\n''') +markup = TexiMarkup () +sys.stderr.write ('''translations-status.py:717: warning: using markup = TexiMarkup (): ugly HTML + output, questionable PDF and info output. + Consider using HTML-only markup = HTMLMarkup ()\n''') -main_status_page = texi_header % locals () + main_status_body + texi_footer +main_status_body = markup.paragraph (markup.emph (last_updated_string % date_time)) +main_status_body += '\n'.join ([doc.texi_status (markup) for doc in master_docs]) +main_status_page = markup.texi (main_status_body) open ('translations.itexi', 'w').write (main_status_page) for l in enabled_languages: date_time = buildlib.read_pipe ('LANG=%s date -u' % l)[0] - updated = translation[l] (last_updated_string) % date_time - texi_status = '\n'.join ([doc.translations[l].texi_status () + updated = markup.paragraph (markup.emph (translation[l] (last_updated_string) % date_time)) + texi_status = '\n'.join ([doc.translations[l].texi_status (markup) for doc in master_docs if l in doc.translations]) - lang_status_page = texi_header + updated + texi_status + texi_footer + lang_status_page = markup.texi (updated + texi_status) open (os.path.join (l, 'translations.itexi'), 'w').write (lang_status_page) main_status_txt = '''Documentation translations status @@ -587,7 +738,7 @@ FT = fully translated ''' % date_time -main_status_txt += '\n'.join ([doc.text_status () for doc in master_docs]) +main_status_txt += '\n'.join ([doc.text_status (markup) for doc in master_docs]) status_txt_file = 'out/translations-status.txt' progress ("Writing %s..." % status_txt_file)