patacrep/sortindex.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
# Generate indexes files for the Crep's chordbook compilation. This is
# a replacement for the original makeindex program written in C that
# produces an index file (.sbx) from a file generated by the latex
# compilation of the songbook (.sxd).
#
# Usage : songbook-makeindex.py src
#         src is the .sxd file generated by latex
#

import sys
import re
import locale
import warnings

# Pattern set to ignore latex command in title prefix
keywordPattern = re.compile(r"^%(\w+)\s?(.*)$")
firstLetterPattern = re.compile(r"^(?:\{?\\\w+\}?)*[^\w]*(\w)")
iecPattern = re.compile(r"\IeC {\\(.*?)}")
replacePattern = {
     '`A': 'À',
     '`a': 'à',
     '^a': 'â',
     "'a": 'á',
     "~a": 'ã',
     'oe': 'œ',
     "'e" : 'é',
     "`e" : 'è',
     "^e" : 'ê',
     '"e' : 'ë',
     "'E" : 'É',
     "`E" : 'È',
     "'o" : 'ó',
     "^o" : 'ô',
     r'"\i' : 'i',
     r'^\i' : 'i',
     '"u' : 'ü',
     '`u' : 'ù',
     '`u' : 'ù',
     '~n' : 'ñ',
     "c C" : 'Ç',
     "c c" : 'ç',
     "textquoteright" : "'",
}

def sortkey(value):
    '''
    From a title, return something usable for sorting. It handles locale (but
    don't forget to call locale.setlocale(locale.LC_ALL, '')). It also try to
    handle the sort with crappy latex escape sequences. Some chars may not be
    handled by this function, so add them to *replacePattern* dictionnary.
    '''
    def repl(match):
        try:
            return replacePattern[match.group(1).strip()]
        except KeyError:
            warnings.warn("Error, no match to replace %s in %s. You should add it in the coresponding table in title_sort.py" % (match.group(0), match.group(1)))

    return locale.strxfrm(iecPattern.sub(repl, value).replace(' ', 'A'))

def processSXDEntry(tab):
    return (tab[0], tab[1], tab[2])

def processSXD(filename):
    file = open(filename)
    data = []
    for line in file:
        data.append(line.strip())
    file.close()

    type = data[0]
    i = 1
    idx = index()

    if len(data) > 1:
        while data[i].startswith('%'):
            keywords = keywordPattern.match(data[i]).groups()
            idx.keyword(keywords[0],keywords[1])
            i += 1

    idx.compileKeywords()
    for i in range(i,len(data),3):
        entry = processSXDEntry(data[i:i+3])
        idx.add(entry[0],entry[1],entry[2])
    return idx

class index:
    data = dict()
    keywords = dict()

    def filter(self, key):
        letter = firstLetterPattern.match(key).group(1)
        if re.match('\d',letter):
            letter = '0-9'
        return (letter.upper(), key)

    def keyword(self, key, word):
        if not self.keywords.has_key(key):
            self.keywords[key] = []
        self.keywords[key].append(word)

    def compileKeywords(self):
        self.prefix_patterns = []
        if 'prefix' in self.keywords:
            for prefix in self.keywords['prefix']:
                self.prefix_patterns.append(re.compile(r"^(%s)\b\s*(.*)$" % prefix))

    def add(self, key, number, link):
        for pattern in self.prefix_patterns:
            match = pattern.match(key)
            if match:
                key = "%s (%s)" % (match.group(2), match.group(1))
                break # Only one match per key
        (first, key) = self.filter(key)
        if not self.data.has_key(first):
            self.data[first] = dict()
        if not self.data[first].has_key(key):
            self.data[first][key] = []
        self.data[first][key].append({'num':number, 'link':link})

    def refToStr(self, ref):
        if sys.version_info >= (2,6):
            return '\\hyperlink{{{0[link]}}}{{{0[num]}}}'.format(ref)
        else:
            return '\\hyperlink{%(link)s}{%(num)s}' % ref

    def entryToStr(self, key, entry):
        if sys.version_info >= (2,6):
            return '\\idxentry{{{0}}}{{{1}}}\n'.format(key, '\\\\'.join(map(self.refToStr, entry)))
        else:
            return '\\idxentry{%s}{%s}\n' % (key, '\\\\'.join(map(self.refToStr, entry)))

    def idxBlockToStr(self, letter, entries):
        str = '\\begin{idxblock}{'+letter+'}'+'\n'
        for key in sorted(entries.keys(), key=sortkey):
            str += self.entryToStr(key, entries[key])
        str += '\\end{idxblock}'+'\n'
        return str

    def entriesToStr(self):
        str = ""
        for letter in sorted(self.data.keys()):
            str += self.idxBlockToStr(letter, self.data[letter])
        return str