Mercurial > dottes
view abcfield.py @ 359:2a7d03d6a89f
Use txt2tags to format intro text.
That way we can include basic markup in the into text and use it in
both LaTeX and HTML.
Take advantage of this to expand the wording of the intro text in all
books.
author | Jim Hague <jim.hague@acm.org> |
---|---|
date | Wed, 21 Aug 2013 10:28:10 +0100 |
parents | 27f29e8aafea |
children | 760d0ae5acea |
line wrap: on
line source
#!/usr/bin/env python # # Extact a text field (title, by default) from a .abc file, and print it out # formatted for use in LaTeX or HTML. # import optparse import sys accentedletters = { # Acute accents "'A" : ("Á", "\\'{A}"), "'E" : ("É", "\\'{E}"), "'I" : ("Í", "\\'{I}"), "'O" : ("Ó", "\\'{O}"), "'U" : ("Ú", "\\'{U}"), "'Y" : ("Ý", "\\'{Y}"), "'a" : ("á", "\\'{a}"), "'e" : ("é", "\\'{e}"), "'i" : ("í", "\\'{i}"), "'o" : ("ó", "\\'{o}"), "'u" : ("ú", "\\'{u}"), "'y" : ("ý", "\\'{y}"), # Grave accents "`A" : ("À", "\\`{A}"), "`E" : ("È", "\\`{E}"), "`I" : ("Ì", "\\`{I}"), "`O" : ("Ò", "\\`{O}"), "`U" : ("Ù", "\\`{U}"), "`a" : ("à", "\\`{a}"), "`e" : ("è", "\\`{e}"), "`i" : ("ì", "\\`{i}"), "`o" : ("ò", "\\`{o}"), "`u" : ("ù", "\\`{u}"), # Umlauts "\"A" : ("Ä", "\\\"{A}"), "\"E" : ("Ë", "\\\"{E}"), "\"I" : ("Ï", "\\\"{I}"), "\"O" : ("Ö", "\\\"{O}"), "\"U" : ("Ü", "\\\"{U}"), "\"Y" : ("Ÿ", "\\\"{Y}"), "\"a" : ("ä", "\\\"{a}"), "\"e" : ("ë", "\\\"{e}"), "\"i" : ("ï", "\\\"{\i}"), "\"o" : ("ö", "\\\"{o}"), "\"u" : ("ü", "\\\"{u}"), "\"y" : ("ÿ", "\\\"{y}"), # Circumflexes "^A" : ("Â", "\\^{A}"), "^E" : ("Ê", "\\^{E}"), "^I" : ("Î", "\\^{I}"), "^O" : ("Ô", "\\^{O}"), "^U" : ("Û", "\\^{U}"), "^a" : ("â", "\\^{a}"), "^e" : ("ê", "\\^{e}"), "^i" : ("î", "\\^{\i}"), "^o" : ("ô", "\\^{o}"), "^u" : ("û", "\\^{u}"), # Tilde "~A" : ("Ã", "\\~{A}"), "~N" : ("Ñ", "\\~{N}"), "~O" : ("Õ", "\\~{O}"), "~a" : ("ã", "\\~{a}"), "~n" : ("ñ", "\\~{n}"), "~o" : ("õ", "\\~{o}"), # Cedilla ",C" : ("Ç", "\\c{C}"), ",c" : ("ç", "\\c{c}"), # Slash "/O" : ("Ø", "\\O"), "/o" : ("ø", "\\o"), # Ring "AA" : ("Å", "\\r{A}"), "aa" : ("å", "\\r{a}"), # Ligatures "AE" : ("Æ", "\\AE"), "ae" : ("æ", "\\ae"), "ss" : ("ß", "\\ss"), } def convertTitle(t, options): res = "" while True: p = t.partition('\\') res += p[0] if p[1] == "": break abc = p[2][0:2] t = p[2][2:] if (options.html or options.latex) and abc in accentedletters: if options.html: res += accentedletters[abc][0] else: res += accentedletters[abc][1] else: res += "\\" + abc return res def process(inf, options): n = options.index for line in inf: line = line.strip() if len(line) > 2 and line[0] == options.field and line[1] == ':': if len(options.contains) > 0: if line.find(options.contains) < 0: continue if n > 1: n = n - 1 else: print(convertTitle(line[2:].strip(), options)) break parser = optparse.OptionParser(usage="usage: %prog [options] [filename]\n\n" " Extract field data from ABC file.") parser.add_option("-f", "--field", dest="field", default="T", help="extract the field FIELD", metavar="FIELD") parser.add_option("-m", "--html", dest="html", action="store_true", default=False, help="format output for HTML") parser.add_option("-l", "--latex", dest="latex", action="store_true", default=False, help="format ouput for LaTeX") parser.add_option("-n", "--index", dest="index", action="store", type="int", default=1, help="report INDEXth value [default: %default]", metavar="INDEX") parser.add_option("-c", "--contains", dest="contains", action="store", type="string", default="", help="report only if line contains CONTENT", metavar="CONTENT") (options, args) = parser.parse_args() if options.html and options.latex: sys.exit("You must choose one of HTML or LaTeX output") if len(args) > 0: for arg in args: try: inf = open(arg, "r") process(inf, options) finally: inf.close() else: process(sys.stdin, options) sys.exit(0)