#!/usr/bin/python

import sys, re, HTMLParser
from path import path

PO = r"""# LightPress wp-frontend language file
# Copyright (c) 2004-2005 L. Magnocavallo, J. Lavigne
# This file is distributed under the same license as the LightPress package.
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
# msgfmt -o locale/it/LC_MESSAGES/wp-frontend.mo locale/it/LC_MESSAGES/wp-frontend
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: Lightpress 1.2\n"
"Report-Msgid-Bugs-To: devteam@lightpress.org\n"
"POT-Creation-Date: 2005-09-21 12:24+0200\n"
"PO-Revision-Date: 2005-09-21 12:39:00+2\n"
"Last-Translator: Ludovico Magnocavallo <ludo@lightpress.org>\n"
"Language-Team: LP Translations <devteam@lightpress.org>\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=UTF-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Plural-Forms: nplurals=2; plural=n != 1;\n"

"""

class LPi18nParser(HTMLParser.HTMLParser):
    
    re_whitespace_left = re.compile(r'\s+<', re.S)
    re_whitespace_right = re.compile(r'>\s+', re.S)
    
    def __init__(self, folder):
        HTMLParser.HTMLParser.__init__(self)
        self._folder_len = len(folder) + 1
        self._file = ''
        self._lines = None
        self._open_tags = []
        self._pos = None
        self.i18n = {}

    def _addi18n(self, text):
        if not text:
            return
        if not text in self.i18n:
            self.i18n[text] = []
        lineno, offset = self.getpos()
        self.i18n[text].append("%s:%s:c%s" % (self._file, lineno, offset))

    def handle_starttag(self, tag, attrs):
#        print >>sys.stderr, "open %s" % tag
        attrs = dict(attrs)
#        print >>sys.stderr, self._file, tag, self.getpos()
        if self._open_tags:
            # child element of an i18n tag
#            print >>sys.stderr, "adding tag %s to open tags" % tag
            self._open_tags.append(tag)
            return
        for name, value in attrs.items():
            if not name.startswith('i18n:'):
                continue
            op = name[5:]
            if op == 'attributes':
                for attr in value.split(';'):
                    self._addi18n(attrs.get(attr, None))
            if op == 'translate':
                if value:
                    self._addi18n(value)
                else:
#                    print >>sys.stderr, "adding tag %s to open tags as i18n tag" % tag
                    self._open_tags.append(tag)

    def handle_data(self, data):
        if self._pos is None and len(self._open_tags) == 1:
#            print >>sys.stderr, "saving pos %s" % self._open_tags
            self._pos = self.getpos()
                    
    def handle_endtag(self, tag):
        if not self._open_tags:
#            print >>sys.stderr, "returning from end tag %s" % tag
            return
        popped_tag = self._open_tags.pop()
        if self._open_tags:
#            print >>sys.stderr, "returning from end tag %s after popping %s" % (tag, popped_tag)
            return
#        print >>sys.stderr, "saving data for tag %s after popping %s, pos %s" % (tag, popped_tag, self.getpos())
        try:
            s_line, s_col = self._pos
        except TypeError, e:
            # no tag data for this tag
            s_line, s_col = self.getpos()
        e_line, e_col = self.getpos()
        s_line -= 1
        lines = self._lines[s_line:e_line]
        if len(lines) == 1:
            lines[0] = lines[0][s_col:e_col]
        else:
            lines[0] = lines[0][s_col:]
            lines[len(lines) - 1] = lines[len(lines) - 1][:e_col]
#        print >>sys.stderr, s_line, s_col, e_line, e_col
#        print >>sys.stderr, self._lines[s_line:e_line]
        data = ''.join(lines).strip()
        data = self.re_whitespace_left.sub(lambda m: ' <', data)
        data = self.re_whitespace_right.sub(lambda m: '> ', data)
        self._addi18n(data)
        self._pos = None
        
    def parse(self, f):
        print >>sys.stderr, "processing %s" % f
        self._file = str(f)[self._folder_len:]
        self._lines = f.lines()
        self.reset()
        try:
            self.feed(''.join(self._lines))
            self.close()
        except HTMLParser.HTMLParseError, e:
            print >>sys.stderr, e
        

if __name__ == '__main__':
    if len(sys.argv) == 1:
        raise SystemExit, "Usage: parser.py MASTERS-FOLDER"
    p = path(sys.argv[1])
    parser = LPi18nParser(sys.argv[1])
    if p.isfile():
        parser.parse(p)
    elif p.isdir():
        for f in p.walkfiles():
            if f.ext in ['.htm', '.html', '.xml', '.txt']:
                parser.parse(f)
    else:
        raise SystemExit, "%s not a file nor a folder. Usage: parser.py MASTERS-FOLDER" % p
    print PO
    keys = parser.i18n.keys()
    keys.sort()
    for k in keys:
        print "# %s" % ', '.join(parser.i18n[k])
        print 'msgid "%s"' % k.replace('\n', '\\n').replace('"', r'\"')
        print 'msgstr ""'
        print