RhodeCode

# set of valid name characters

valid_name_chars = '[\w\-:]'

#

# define global regular expression variables

#

author_rex = re.compile('\s+and\s+')

rembraces_rex = re.compile('[{}]')

capitalize_rex = re.compile('({\w*})')

# used by bibtexkeywords(data)

keywords_rex = re.compile('[,;]')

# used by concat_line(line)

concatsplit_rex = re.compile('\s*#\s*')

# split on {, }, or " in verify_out_of_braces

delimiter_rex = re.compile('([{}"])',re.I)

field_rex = re.compile('\s*(\w*)\s*=\s*(.*)')

data_rex = re.compile('\s*(\w*)\s*=\s*([^,]*),?')

url_rex = re.compile('\\\url\{([^}]*)\}')

#

# return the string parameter without braces

#

def transformurls(str):

    return url_rex.sub(r'<a href="\1">\1</a>', str)

#

# return the string parameter without braces

#

def removebraces(str):

    return rembraces_rex.sub('', str)

#

# latex-specific replacements

# (do this after braces were removed)

#

def latexreplacements(line):

    line = string.replace(line, '~', ' ')

    line = string.replace(line, '\\\'a', 'á')

    line = string.replace(line, '\\"a', 'ä')

    line = string.replace(line, '\\\'e', 'é')

    line = string.replace(line, '\\"e', 'ë')

    line = string.replace(line, '\\\'i', 'í')

    endtype_rex = re.compile('}\s*$')

    endtag_rex = re.compile('^\s*}\s*$')

    bracefield_rex = re.compile('\s*(\w*)\s*=\s*(.*)')

    bracedata_rex = re.compile('\s*(\w*)\s*=\s*{(.*)},?')

    quotefield_rex = re.compile('\s*(\w*)\s*=\s*(.*)')

    quotedata_rex = re.compile('\s*(\w*)\s*=\s*"(.*)",?')

    for line in filecont_source:

        line = line[:-1]

        # encode character entities

        line = string.replace(line, '&', '&')

        line = string.replace(line, '<', '&lt;')

        line = string.replace(line, '>', '>')

        # start entry: publication type (store for later use)

        if pubtype_rex.match(line):

        # want @<alphanumeric chars><spaces>{<spaces><any chars>,

            entrycont = {}

            entry = []

            entrytype = pubtype_rex.sub('\g<1>',line)

            entrytype = string.lower(entrytype)

        # end entry if just a }

        elif endtype_rex.match(line):

            # generate doxygen code for the entry

            # enty type related formattings

            if entrytype in ('book', 'inbook'):

                entrycont['title'] = '<em>' + entrycont['title'] + '</em>'

                if not entrycont.has_key('author'):

                    entrycont['author'] = entrycont['editor']

                    entrycont['author']['text'] += ', editors'

            elif entrytype == 'article':

                entrycont['journal'] = '<em>' + entrycont['journal'] + '</em>'

            elif entrytype in ('inproceedings', 'incollection', 'conference'):

                entrycont['booktitle'] = '<em>' + entrycont['booktitle'] + '</em>'

            elif entrytype == 'techreport':

                if not entrycont.has_key('type'):

                    entrycont['type'] = 'Technical report'

            elif entrytype == 'mastersthesis':

                entrycont['type'] = 'Master\'s thesis'

            elif entrytype == 'phdthesis':

                entrycont['type'] = 'PhD thesis'

            for eline in entrycont:

                else:

                    entry.append(entrycont['year'] + '.')

            if entrycont.has_key('note') and (entrycont['note'] != ''):

                entry.append(entrycont['note'] + '.')

            # generate keys for sorting and for the output

            sortkey = ''

            bibkey = ''

            if entrycont.has_key('author'):

                for author in entrycont['author']['list']:

                    sortkey += copychars(author, author.rfind(' ')+1, len(author))

                bibkey = entrycont['author']['abbrev']

            else:

                bibkey = 'x'

            if entrycont.has_key('year'):

                sortkey += entrycont['year']

                bibkey += entrycont['year'][-2:]

            if entrycont.has_key('title'):

                sortkey += entrycont['title']

            if entrycont.has_key('key'):

                sortkey = entrycont['key'] + sortkey

                bibkey = entrycont['key']

            entry.insert(0, sortkey)

            entry.insert(1, bibkey)

            # add the entry to the file contents

            filecont.append(entry)

        else:

            # field, publication info

            field = ''

            data = ''

            # field = {data} entries

            if bracedata_rex.match(line):

                field = bracefield_rex.sub('\g<1>', line)

                field = string.lower(field)

                data =  bracedata_rex.sub('\g<2>', line)

            # field = "data" entries

            elif quotedata_rex.match(line):

                field = quotefield_rex.sub('\g<1>', line)

                field = string.lower(field)

                data =  quotedata_rex.sub('\g<2>', line)

            # field = data entries

            elif data_rex.match(line):

                field = field_rex.sub('\g<1>', line)

                line = latexreplacements(line)

                entrycont[field] = line

    # sort entries

    filecont.sort(entry_cmp)

    # count the bibtex keys

    keytable = {}

    counttable = {}

    for entry in filecont:

        bibkey = entry[1]

        if not keytable.has_key(bibkey):

            keytable[bibkey] = 1

        else:

            keytable[bibkey] += 1

    for bibkey in keytable.keys():

        counttable[bibkey] = 0

    # generate output

    for entry in filecont:

        # generate output key form the bibtex key

        bibkey = entry[1]

        if keytable[bibkey] == 1:

            outkey = bibkey

        else:

            outkey = bibkey + chr(97 + counttable[bibkey])

        counttable[bibkey] += 1

        # append the entry code to the output

            file.append(line)

        file.append('')

    return file

#

# return 1 iff abbr is in line but not inside braces or quotes

# assumes that abbr appears only once on the line (out of braces and quotes)

#

def verify_out_of_braces(line, abbr):

    phrase_split = delimiter_rex.split(line)

    abbr_rex = re.compile( '\\b' + abbr + '\\b', re.I)

    open_brace = 0

    open_quote = 0

    for phrase in phrase_split:

        if phrase == "{":

            open_brace = open_brace + 1

        elif phrase == "}":

            open_brace = open_brace - 1

        elif phrase == '"':

        filecont[i] = line + '\n'

        i = i+1

    # get rid of the extra stuff at the end of the array

    # (The extra stuff are duplicates that are in the array because

    # blank lines were removed.)

    length = len( filecont)

    filecont[length-j:length] = []

    return filecont

def filehandler(filepath):

    try:

        fd = open(filepath, 'r')

        filecont_source = fd.readlines()

        fd.close()

    except:

        print 'Could not open file:', filepath

    washeddata = bibtexwasher(filecont_source)

    outdata = bibtexdecoder(washeddata)

    print '/**'

    print '\page references References'

    print

    for line in outdata:

        print line

    print '*/'

# main program

def main():

    import sys

    if sys.argv[1:]:

        filepath = sys.argv[1]

    else:

        print "No input file"

        sys.exit()

    filehandler(filepath)

if __name__ == "__main__": main()

# end python script