X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=buildscripts%2Fhtml-gettext.py;h=ccfe6937c0316ec354e2116239475338951a719d;hb=03302c2f0fec2ccf1484b1ab316f90d4c17b786d;hp=7b381349b56fc4cd8a59b66b714382e9c5713ecd;hpb=fb48408d6e0c1b46f818dc56a218da5e88ef4ed3;p=lilypond.git diff --git a/buildscripts/html-gettext.py b/buildscripts/html-gettext.py index 7b381349b5..ccfe6937c0 100644 --- a/buildscripts/html-gettext.py +++ b/buildscripts/html-gettext.py @@ -1,7 +1,7 @@ #!@PYTHON@ # html-gettext.py -# USAGE: html-gettext.py [-o OUTDIR] BUILDSCRIPT-DIR LOCALEDIR LANG FILES +# USAGE: html-gettext.py [-o OUTDIR] LANG FILES # # -o OUTDIR specifies that output files should be written in OUTDIR # rather than be overwritten @@ -11,90 +11,116 @@ import sys import re import os import getopt -import gettext + +import langdefs optlist, args = getopt.getopt(sys.argv[1:],'o:') -buildscript_dir, localedir, lang = args[0:3] +lang = args[0] +files = args [1:] outdir = '.' for x in optlist: - if x[0] == '-o': - outdir = x[1] - -sys.path.append (buildscript_dir) -import langdefs + if x[0] == '-o': + outdir = x[1] double_punct_char_separator = langdefs.LANGDICT[lang].double_punct_char_sep -t = gettext.translation('lilypond-doc', localedir, [lang]) -my_gettext = t.gettext +my_gettext = langdefs.translation[lang] html_codes = ((' -- ', ' – '), - (' --- ', ' — ')) -html2texi = {'command': (re.compile (r'(.*?)'), r'@command{\1}'), - 'code': (re.compile (r'(.*?)'), r'@code{\1}') - } -texi2html = {'command': (re.compile (r'@command{(.*?)}'), r'\1'), - 'code': (re.compile (r'@code{(.*?)}'), r'\1') - } + (' --- ', ' — '), + ("'", '’')) +texi_html_conversion = { + 'command': { + 'html2texi': + (re.compile (r'(?:|)(.*?)(?:|)'), + r'@command{\1}'), + 'texi2html': + (re.compile (r'@command{(.*?)}'), + r'\1'), + }, + 'code': { + 'html2texi': + (re.compile (r'(.*?)'), + r'@code{\1}'), + 'texi2html': + (re.compile (r'@code{(.*?)}'), + r'\1'), + }, + } + whitespaces = re.compile (r'\s+') def _ (s): - if not s: - return '' - s = whitespaces.sub (' ', s) - for c in html_codes: - s = s.replace (c[1], c[0]) - for u in html2texi.values(): - s = u[0].sub (u[1], s) - s = my_gettext (s) - for u in texi2html.values(): - s = u[0].sub (u[1], s) - for c in html_codes: - s = s.replace (c[0], c[1]) - return s + if not s: + return '' + str = whitespaces.sub (' ', s) + for c in html_codes: + str = str.replace (c[1], c[0]) + for command in texi_html_conversion: + d = texi_html_conversion[command] + str = d['html2texi'][0].sub (d['html2texi'][1], str) + str = my_gettext (str) + str = d['texi2html'][0].sub (d['texi2html'][1], str) + for c in html_codes: + str = str.replace (c[0], c[1]) + return str + +link_re = re.compile (r'') def link_gettext (m): - return '' + return '' -def title_gettext (m): - return '' + _(m.group(1)) + ' - ' + m.group(2) + '' +makeinfo_title_re = re.compile (r'([^<]*?) - ([^<]*?)') + +def makeinfo_title_gettext (m): + return '' + _ (m.group (1)) + ' - ' + m.group (2) + '' + +texi2html_title_re = re.compile (r'(.+): ([A-Z\d.]+ |)(.+?)') + +def texi2html_title_gettext (m): + return '' + _ (m.group (1)) + double_punct_char_separator + ': ' \ + + m.group (2) + _ (m.group (3)) + '' + +a_href_re = re.compile ('(?s)[^>]*?href="[\\w.#-_]+"[^>]*?>)(?P)?\ +(?PAppendix )?(?P[A-Z0-9.]+ | (?:<){1,2} | [^>:]+?: | |)\ +(?P(?:|||[^>])+?)(?P(?(code)|))\ +(?P (?:>){1,2} | |):?') def a_href_gettext (m): - s = '' - if m.group(0)[-1] == ':': - s = double_punct_char_separator + ':' - t = '' - if m.lastindex == 7: - t = m.group(7) - return '' + s + s = '' + if m.group(0)[-1] == ':': + s = double_punct_char_separator + ':' + t = '' + if m.group ('appendix'): + t = _ (m.group ('appendix')) + return '' + s + +h_re = re.compile (r'\s*(Appendix |)([A-Z\d.]+ |)(.+?)\s*') def h_gettext (m): - if m.group (3): - s = _(m.group(3)) - else: - s= '' - return '' + s +\ - m.group(4) + _(m.group(5)) + '' - -def crossmanual_ref_gettext (m): - return '' + _(m.group(2)) + '' - -for filename in args[3:]: - f = open (filename, 'r') - page = f.read () - f.close() - page = re.sub (r'', link_gettext, page) - page = re.sub (r'([^<]*?) - ([^<]*?)', title_gettext, page) - # ugh - page = re.sub (r'(?ms))()?(Appendix )?([A-Z\d.]+ |)(.+?)(?(3)):?', a_href_gettext, page) - page = re.sub (r'\s*(Appendix |)([A-Z\d.]+ |)?([^<]*[^< ])\s*', h_gettext, page) - page = re.sub (r'(.+?)', crossmanual_ref_gettext, page) - # this is necessary for entries not translated by a_href_gettext - page = re.sub (r'(.+?)', crossmanual_ref_gettext, page) - for w in ('Next:', 'Previous:', 'Up:'): - page = re.sub (w, _(w), page) - page = langdefs.LANGDICT[lang].html_filter (page) - f = open (os.path.join (outdir, filename), 'w') - f.write (page) - f.close () + if m.group (3): + s = _ (m.group (3)) + else: + s= '' + return '' + s +\ + m.group (4) + _ (m.group (5)) + '' + +for filename in files: + f = open (filename, 'r') + page = f.read () + f.close () + page = link_re.sub (link_gettext, page) + page = makeinfo_title_re.sub (makeinfo_title_gettext, page) + page = texi2html_title_re.sub (texi2html_title_gettext, page) + page = a_href_re.sub (a_href_gettext, page) + page = h_re.sub (h_gettext, page) + for w in ('Next:', 'Previous:', 'Up:'): + page = page.replace (w, _ (w)) + page = langdefs.LANGDICT[lang].html_filter (page) + f = open (os.path.join (outdir, filename), 'w') + f.write (page) + f.close ()