\n")
self.figureFlag = False
elif self.token == "\\begin{verbatim}":
sequence.append("\n\n")
while 1:
line = self.scanner.getRawLine()
if line.find("\\end{verbatim}") >= 0: break
else: sequence.append(line)
sequence.append("\n\n")
elif self.token == "\\begin{abstract}":
if LANG=="de": sequence.append("\n
Zusammenfassung:
\n")
else: sequence.append("\n
Abstract:
\n")
elif self.token == "\\end{thebibliography}":
while (sequence[-1][1:4] == "\12\12")
elif (self.token == "\\item") or (self.token[1:8] == "bibitem"):
while (sequence[-1][1:4] == "\12", "\12"]):
sequence.append("
\12\12")
sequence.append("- ")
if self.citeFlag and self.token[1:8] == "bibitem":
sequence.append("("+self.readableBibKey(self.token[9:-1])+") ")
ptag = 0
elif self.token in ["\\end{center}", "\\end{flushleft}", "\\end{flushright}"]:
palign = ''
sequence.append("\12\12")
elif self.token == "":
if sequence[-1][0:2] == "\12")
if not (self.token in (TermPSequence+["}"])):
self.token = self.getToken()
while self.token == " ": self.token = self.getToken()
return sequence
def mainContent(self):
sequence = self.sequenceOfParagraphs()
if len(sequence) > 0 and sequence[-1][0:2] == " 0) or (self.token == "\\chapter{")) and (depth < self.mindepth):
self.mindepth = depth
self.chapter[depth] = self.chapter[depth] + 1
self.chapter = self.chapter[0:depth+1]
for i in range(depth, 5) : self.chapter.append(0)
cn = ""
if depth <= CHAPTERNUMBERING_DEPTH:
flag = 0
for i in range(0, depth+1):
if flag or (self.chapter[i] > 0):
cn = cn + repr(self.chapter[i]) + "."
flag = 1
if len(cn) > 0: cn = cn[:-1] # chop
self.chapterName = cn
self.token = self.getToken()
if cn <> "": s = cn + " " #+ self.token
else: s = "" #+self.token
s += "".join(self.sequenceOfWords())
# self.token = self.getToken()
# while self.token <> "}":
# s = s + self.token
# self.token = self.getToken()
self.depth = depth # depth zurückgeben
return s
def Parse(self):
global PROJECT_TITLE, AUTHOR, REFERENCE, DATE
self.token = self.getToken()
while self.token <> "\\begin{document}":
self.token = self.getToken()
while 1:
if self.token == "\\end{document}": break
elif self.token == "\\begin{titlepage}":
self.token = self.getToken()
self.currPage = HTMLPage(DESTINATION_NAME + ENDING,
PROJECT_TITLE, "TitlePage")
self.mainContent()
if self.token <> "\\end{titlepage}":
raise ParserError, "\\end{titlepage} expected"
self.pageList.append(self.currPage)
self.pageList.append(HTMLPage("toc"+ENDING, TOC_TITLE,
"TableOfContents"))
self.token = self.getToken()
elif self.token == "\\maketitle":
self.currPage = HTMLPage(DESTINATION_NAME + ENDING,
PROJECT_TITLE, "TitlePage")
self.currPage.body.append('
'+\
PROJECT_TITLE+'
')
self.currPage.body.append('\n'+AUTHOR_STR+": "+AUTHOR+'
\n')
self.currPage.body.append(''+DATE_STR+": "+DATE+'
')
self.token = self.getToken(); self.mainContent()
self.pageList.append(self.currPage)
self.pageList.append(HTMLPage("toc"+ENDING, TOC_TITLE,
"TableOfContents"))
elif self.token in SECTIONS:
s = self.ParseHeading()
self.nodeCount = self.nodeCount + 1
self.currPage = HTMLPage("node"+repr(self.nodeCount)+ENDING, \
s, "NormalPage", self.chapter)
while 1:
self.currPage.body.append(HeadT[self.depth] + s + HeadTE[self.depth]+"\12\12")
self.token = self.getToken()
self.mainContent()
if self.token in SECTIONS:
t = self.currPage.body[-1]
while (len(t) > 0) and (t[-1:] <= " "): t = t[:-1]
t = t[-5:]
if (t in HeadTE):
s = self.ParseHeading()
else: break
else: break
self.pageList.append(self.currPage)
elif self.token == "\\begin{thebibliography}":
self.nodeCount = self.nodeCount + 1
self.chapter = [0, 0, 0, 0, 0, 0]
self.chapter[self.mindepth] = 1
self.currPage = HTMLPage("node"+repr(self.nodeCount)+ENDING, \
BIBLIOGRAPHY_TITLE, "NormalPage", self.chapter)
self.mainContent()
self.pageList.append(self.currPage)
else:
if self.token[1:6] == "title":
# PROJECT_TITLE = self.readStr()
self.token = self.getToken()
PROJECT_TITLE = "".join(self.sequenceOfWords())
elif self.token[1:7] == "author":
AUTHOR = self.readStr()
if REFERENCE == "reference to author ?": REFERENCE = AUTHOR
elif self.token[1:5] == "date": DATE = self.readStr()
self.token = self.getToken()
while not self.scanner.eof: s = self.scanner.getLine()
self.flushPageList()
self.writeImages()
texFileName = ""
i = 1
while i < len(sys.argv):
if sys.argv[i][0:1] == "-":
if sys.argv[i][0:2] == "-t":
i += 1
PROJECT_TITLE = sys.argv[i]
elif sys.argv[i][0:2] == "-a":
i += 1
AUTHOR = sys.argv[i]
if REFERENCE == "reference to author ?": REFERENCE = AUTHOR
elif sys.argv[i][0:2] == "-r":
i += 1
REFERENCE = sys.argv[i]
elif sys.argv[i][0:2] == "-p":
i += 1
PDFURL = sys.argv[i]
elif sys.argv[i][0:2] == "-e":
i+= 1
SLIDESURL = sys.argv[i]
elif sys.argv[i][0:2] == "-c":
i += 1
TOC_TITLE = sys.argv[i]
elif sys.argv[i][0:2] == "-b":
i += 1
BIBLIOGRAPHY_TITLE = sys.argv[i]
elif sys.argv[i][0:2] == "-d":
i += 1
DESCRIPTION = sys.argv[i]
elif sys.argv[i][0:2] == "-k":
i += 1
KEYWORDS = sys.argv[i]
elif sys.argv[i][0:2] == "-s":
i += 1
DESTINATION_NAME = sys.argv[i]
elif sys.argv[i][0:2] == "-l":
i += 1
LANG = sys.argv[i]
elif sys.argv[i][0:2] == "-x":
HTMLPageHead = '' + HTMLPageHead
ENDING = ".xhtml"
elif sys.argv[i][0:2] == "-i":
INDEX_FILE = "toc.html"
else: texFileName = sys.argv[i]
i += 1
# debugging: texFileName = "Kritik.tex"
if texFileName == "":
print '''
Usage:
latex2html.py [OPTION] texfile
Options:
-t name : project title
-a name : author
-r name : reference to the author (may include HTML-tags)
-p url : valid url of a PDF Version of the document
-e url : valid url of a related beamer presentation
-c name : TOC title (default: "Table of Contents")
-b name : bibliography title (default: "Bibliography")
-d name : short description
-k name : list of keywords
-s name : name of destination directory (default: texfile)
-l name : language (e.g. "en-US")
-x : create xhtml instead of html pages
-i : duplicate table of contents as "index.html" file
'''
else:
if DESTINATION_NAME == "destination ?":
if texFileName[-4:] == ".tex": DESTINATION_NAME = texFileName[:-4]
else: DESTINATION_NAME = texFileName + "www"
if LANG == "de":
TOC_TITLE = "Inhaltsverzeichnis"
BIBLIOGRAPHY_TITLE = "Literaturverzeichnis"
AUTHOR_STR = "Autor"
DATE_STR = "Datum"
scanner=TexScanner(texFileName)
parser=TexParser(scanner)
parser.Parse()
#while not scanner.eof:
# print parser.getToken()
