#!/usr/bin/env python # coding: utf-8 import sys, string, getopt, xml.dom.minidom class handler: def __init__(self): self.functions = { } self.file = None self.format = None self.extension = None def run_function(self, name, node): if self.functions.has_key(name): self.functions[name](node) def open(self, filename = None, basename = None): if filename is None: if basename is None: basename = "resume" filename = basename + "." + self.extension if filename == "-": self.file = sys.stdout else: self.file = file(filename, "wb") return self.file def close(self): self.file.close() def write(self, data): self.file.write(data.encode("utf-8", "replace")) def start(self, root): pass def end(self, root): pass def separate(self, a, b): pass def wrap(self, text, indent = "", firstindent = None, column = 0, width = 72, min_width = 0): result = "" i = 0 while i < len(text) and text[i] in string.whitespace: i = i + 1 if firstindent is None: firstindent = indent ind = firstindent while i < len(text): ind_length = len(ind.expandtabs()) p = i while i < len(text) and text[i] not in string.whitespace: i += 1 if column != 0 and column + i - p + 1 > width and column + i - p + 1 - ind_length >= min_width: result += "\n" column = 0 if column == 0: result += ind column += ind_length else: result += " " column += 1 result += text[p:i] column += i - p while i < len(text) and text[i] in string.whitespace: i += 1 ind = indent result += "\n" return result class handler_text(handler): def __init__(self): handler.__init__(self) self.format = "text" self.extension = "txt" self.functions = { "header": self.header, "blurb": self.blurb, "par": self.par, "category": self.category } def separate(self, a, b): if self.functions.has_key(a) and self.functions.has_key(b): self.write("\n") if a == "pagebreak": self.write("\n") def escape(self, str): tmp = "" for c in str: if ord(c) == 160: # Non-breaking space. It might break. s = " " elif ord(c) == 233: s = "e" elif ord(c) == 0x2013: s = "-" elif ord(c) == 0x2014: s = "--" elif ord(c) == 0x2018: s = "'" elif ord(c) == 0x2019: s = "'" elif ord(c) == 0x201C: s = "\"" elif ord(c) == 0x201D: s = "\"" elif ord(c) >= 128: s = "" else: s = c tmp = tmp + s return tmp def read_text(self, node): def recurse(node): text = "" for child in node.childNodes: if child.nodeType in [ xml.dom.Node.TEXT_NODE, xml.dom.Node.CDATA_SECTION_NODE ]: text += child.data elif child.nodeType == xml.dom.Node.ELEMENT_NODE: text += recurse(child) return text return recurse(node) def header(self, node): for name in [ "name", "title", "phone", "web", "email" ]: attr = node.getAttributeNode(name) if attr is not None: self.write(self.escape(attr.nodeValue) + "\n") def blurb(self, node): self.par(node); def par(self, node): self.write(self.wrap(self.escape(self.read_text(node)))) def category(self, node): def recurse(node, level = 0): if node.nodeType != xml.dom.Node.ELEMENT_NODE: return if node.localName == "category": attr = node.getAttributeNode("name") if attr is not None: name = attr.nodeValue else: name = None if (level < 0): level = 0 if name is not None: self.write(self.wrap(self.escape(name), indent = " " * level)) for child in node.childNodes: recurse(child, level + 1) elif node.localName == "item": self.write(self.wrap(self.escape(self.read_text(node)), firstindent = " " * level + "* ", indent = " " * (level + 1))) recurse(node) class handler_html(handler): def __init__(self): handler.__init__(self) self.format = "HTML" self.extension = "html" self.functions = { "header": self.header, "blurb": self.blurb, "par": self.par, "category": self.category } def escape(self, str): tmp = "" for c in str: if c == "&": s = "&" elif c == "<": s = "<" elif c == ">": s = "&rt;" elif c == "\"": s = """ elif c == "'": s = "'" elif ord(c) == 160: # Non-breaking space s = " " elif ord(c) >= 128: s = "&#%d;" % ord(c) else: s = c tmp = tmp + s return tmp def read_text(self, node): def recurse(node): text = "" for child in node.childNodes: if child.nodeType in [ xml.dom.Node.TEXT_NODE, xml.dom.Node.CDATA_SECTION_NODE ]: text += self.escape(child.data) elif child.nodeType == xml.dom.Node.ELEMENT_NODE: if child.localName == "link": text += "" + recurse(child) + "" elif child.localName == "cite": text += "" + recurse(child) + "" else: text += recurse(child) return text return recurse(node) def start(self, root): self.write("""\ """ + self.escape(root.getAttribute("title")) + """ """) def end(self, root): self.write("""\ """) def separate(self, a, b): if a == "header": self.write("\t\t
\n") def header(self, node): self.write("\t\t

\n") attr = node.getAttributeNode("name") if attr is not None: self.write("\t\t" + self.escape(attr.nodeValue) + "
\n") for name in [ "title", "phone" ]: attr = node.getAttributeNode(name) if attr is not None: self.write("\t\t" + self.escape(attr.nodeValue) + "
\n") attr = node.getAttributeNode("web") if attr is not None: self.write("\t\t " + self.escape(attr.nodeValue) + "
\n") attr = node.getAttributeNode("email") if attr is not None: self.write("\t\t " + self.escape(attr.nodeValue) + "
\n") self.write("\t\t

\n") def blurb(self, node): text = "\t\t

\n" + self.wrap(self.read_text(node), indent = "\t\t") + "\t\t

\n" self.write(text) def par(self, node): text = "\t

\n" + self.wrap(self.read_text(node), indent = "\t") + "\t

\n" self.write(text) def category(self, node): def recurse(node, level = 0): if (node.nodeType != xml.dom.Node.ELEMENT_NODE) or (node.localName != "category"): return attr = node.getAttributeNode("name") if attr is not None: name = attr.nodeValue else: name = None if level < 0: level = 0 self.write(self.wrap("
  • " + self.escape(name) + "", indent = "\t" * (level + 3), min_width = 40)) self.write("\t" * (level + 3) + "\n") self.write(self.wrap("
    • ", indent = "\t" * (level + 3), min_width = 40)) self.write("\t" * 2 + "\n") class handler_tex(handler): def __init__(self): handler.__init__(self) self.format = "TeX" self.extension = "tex" self.functions = { "header": self.header, "pagebreak": self.pagebreak, "blurb": self.blurb, "par": self.par, "category": self.category } def escape(self, str): # See the TeXbook, chapter 7, page 38 tmp = "" for c in str: if c == "\\": s = "\\backslash" elif c == "{": s = "$\\{$" elif c == "}": s = "$\\}$" elif c == "$": s = "\\$" elif c == "%": s = "\\%" elif c == "&": s = "\\&" elif c == "#": s = "\\#" elif c == "_": s = "\\_" elif ord(c) == 160: # Non-breaking space s = "~" elif ord(c) == 233: s = "\\'e" elif ord(c) == 0x2013: s = "--" elif ord(c) == 0x2014: s = "---" elif ord(c) == 0x2018: s = "`" elif ord(c) == 0x2019: s = "'" elif ord(c) == 0x201C: s = "``" elif ord(c) == 0x201D: s = "''" elif ord(c) >= 128: s = "" else: s = c tmp = tmp + s return tmp def read_text(self, node): def recurse(node, lower = 0): text = "" for child in node.childNodes: if child.nodeType in [ xml.dom.Node.TEXT_NODE, xml.dom.Node.CDATA_SECTION_NODE ]: tmp = child.data if lower: tmp = tmp.lower() text += self.escape(tmp) elif child.nodeType == xml.dom.Node.ELEMENT_NODE: if child.localName == "cite": text += "{\\sl " + recurse(child) + "}" elif child.localName == "sc": text += "{\\sc " + recurse(child, lower = 1) + "}" else: text += recurse(child) return text return recurse(node) def start(self, root): self.write("""\ \\nopagenumbers \\font\\bigrm = cmr17 \\font\\bigbf = cmbx12 at 17 pt \\font\\medsf = cmss12 at 14 pt \\font\\rm = cmr12 \\font\\sf = cmss12 \\font\\tt = cmtt12 \\font\\sc = cmcsc10 at 12 pt \\font\\sl = cmsl12 \\rm \\vbox to 0 pt {} """) def end(self, root): self.write("""\ \\vfill \\eject \\end """) def separate(self, a, b): if a in [ "header", "blurb" ] or b in [ "header", "blurb" ]: self.write(""" \\bigskip """) def header(self, node): attr = node.getAttributeNode("name") if attr is not None: self.write(r"\centerline {\bigbf " + self.escape(attr.nodeValue) + "}\n") attr = node.getAttributeNode("title") if attr is not None: self.write(r"\centerline {\sf " + self.escape(attr.nodeValue) + "}\n") attr = node.getAttributeNode("phone") if attr is not None: self.write(r"\centerline {\sf " + self.escape(attr.nodeValue).replace(" ", r"\thinspace ") + "}\n") for name in [ "web", "email" ]: attr = node.getAttributeNode(name) if attr is not None: self.write(r"\centerline {\tt " + self.escape(attr.nodeValue) + "}\n") def pagebreak(self, node): self.write("""\ \\vfill \\eject """) def blurb(self, node): text = """\ \\noindent \\hfil \\vbox { \\hsize = 4.25 in \\noindent """ + self.wrap(self.read_text(node)) + """\ } \\hfil """ self.write(text) def par(self, node): text = "\\noindent\n" + self.wrap(self.read_text(node)) self.write(text) def category(self, node): def recurse(node, level = 0): if node.nodeType != xml.dom.Node.ELEMENT_NODE: return if node.localName == "category": attr = node.getAttributeNode("name") if attr is not None: name = attr.nodeValue else: name = None if level < 0: level = 0 if name is not None: if level == 0: self.write(self.wrap("\\noindent {\\medsf " + self.escape(name) + "}")) elif level == 1: self.write(self.wrap("\\item {} {\\sf " + self.escape(name) + "}")) else: self.write(self.wrap("\\itemitem {} {\\sf " + self.escape(name) + "}")) for child in node.childNodes: recurse(child, level + 1) elif node.localName == "item": if level == 1: self.write("\\item {}\n") else: self.write("\\itemitem {}\n") self.write(self.wrap(self.read_text(node))) recurse(node) self.write("\\smallskip\n") xml_handlers = [ handler_text(), handler_html(), handler_tex() ] filename = "resume.xml" output_formats = [ "html" ] output_filename = None try: opts, args = getopt.getopt(sys.argv[1:], "f:ho:", [ "formats=", "help", "output=" ]) except getopt.GetoptError: print "Bad option" sys.exit(1) for opt, arg in opts: if opt in [ "-f", "--formats" ]: output_formats = arg.lower().split(",") if opt in [ "-o", "--output" ]: output_filename = arg if opt in [ "-h", "--help" ]: print "Help!" for handler in xml_handlers: print handler.format if len(args) == 1: filename = args[0] elif len(args) > 1: print "Too many filenames" sys.exit(1) handlers = [] for handler in xml_handlers: if handler.format.lower() in output_formats: handlers.append(handler) if output_filename is not None and len(handlers) != 1: print "You may not specify an output file when using more than one format" sys.exit(1) resume = xml.dom.minidom.parse(filename).documentElement for handler in handlers: handler.open(output_filename) handler.start(resume) prev_node_name = None for node in resume.childNodes: if node.nodeType != xml.dom.Node.ELEMENT_NODE: continue node_name = node.localName for handler in handlers: handler.separate(prev_node_name, node_name) handler.run_function(node_name, node) prev_node_name = node_name for handler in handlers: handler.separate(node_name, None) for handler in handlers: handler.end(resume) handler.close()