Created
November 12, 2010 23:14
-
-
Save nathans/674883 to your computer and use it in GitHub Desktop.
SBLGNT parser, basic framework for openscriptures import
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! /usr/bin/evn python | |
import xml.sax | |
class SBLGNTParser(xml.sax.handler.ContentHandler): | |
"""Class to parse the SBL GNT XML file""" | |
def __init__(self, parent): | |
self.init_meta_data() | |
self.parent = parent | |
def init_meta_data(self): | |
self.in_book = 0 | |
self.in_book_title = 0 | |
self.in_paragraph = 0 | |
self.in_verse = 0 | |
self.in_word = 0 | |
self.in_suffix = 0 | |
def startElement(self, name, attrs): | |
if name == "book": | |
self.in_book = 1 | |
elif name == "title": | |
self.in_book_title = 1 | |
elif name == "verse-number": | |
self.in_verse = 1 | |
elif name == "w": | |
self.in_word = 1 | |
elif name == "suffix": | |
self.in_suffix = 1 | |
def characters(self, data): | |
if self.in_word or self.in_suffix: | |
# Here handle tokens | |
self.parent.add_token(data) | |
elif self.in_book or self.in_book_title or self.in_verse: | |
# Here handle structs | |
self.parent.add_token(data) | |
def endElement(self, name): | |
self.init_meta_data() | |
class Command(): | |
def __init__(self): | |
self.test = 1 | |
self.handler = SBLGNTParser(self) | |
self.parser = xml.sax.make_parser() | |
self.parser.setContentHandler(self.handler) | |
def handle(self): | |
self.parser.parse("/Users/sminatha/Downloads/SBLGNTxml/sblgnt.xml") | |
def add_token(self, data): | |
print data | |
if __name__ == "__main__": | |
test = Command() | |
test.handle() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Coolness.