dottes/abcfield.py

#!/usr/bin/env python
#
# Extact a text field (title, by default) from a .abc file, and print it out
# with any ABC accented characters converted to HTML (default) or Latex.
# Recognise continuation fields and print those too.
#

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 convertField(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 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
    found = False
    for line in inf:
        line = line.strip()
        if len(line) > 2 and line[1] == ':':
            if found:
                if line[0] != '+':
                    break
                line = line[2:].strip()
            elif line[0] == options.field:
                if n > 1:
                    n = n - 1
                    continue
                else:
                    line = line[2:].strip()
                    if len(options.starts) > 0:
                        if line.find(options.starts) == 0:
                            line = line[len(options.starts):].strip()
                        else:
                            continue
            else:
                continue
            found = True
            print(convertField(line, options))
    return found

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("-l", "--latex", dest="latex",
                  action="store_true", default=False,
                  help="convert special characters 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("-s", "--starts", dest="starts",
                  action="store", type="string", default="",
                  help="report only if line starts CONTENT and remove CONTENT",
                  metavar="CONTENT")
(options, args) = parser.parse_args()

res = False
if len(args) > 0:
    for arg in args:
        try:
            inf = open(arg, "r")
            res = res or process(inf, options)
        finally:
            inf.close()
else:
    res = process(sys.stdin, options)
sys.exit(int(not res))