danielrichman/git_pygmentize.py

## git_pygmentize.py
#!/usr/bin/python

import sys
import copy
import errno
import os
import git
import pygments
import pygments.lexers
import pygments.formatters

def skip(blob):
    # don't even consider gitignore and .pdf .odt
    if blob.name.endswith(".pdf") or blob.name.endswith(".odt"):
        return True
    if blob.name == ".gitignore":
        return True
    return False

def target(path, rel=False, raw=False):
    assert ".." not in path
    assert not path.startswith("/") and not path.endswith("/")
    assert path
    if raw:
        path = "_raw/" + path
    if not rel:
        path = "html/" + path
    if not raw:
        path += ".html"
    return path

def make_dirs(tgt):
    tgt_dir = os.path.dirname(tgt)
    try:
        os.makedirs(tgt_dir)
        pass
    except OSError as e:
        if e.errno == errno.EEXIST:
            pass
        else:
            raise
    else:
        print "Created directory", tgt_dir

def process(blob):
    tgt = target(blob.path)
    data = blob.data_stream.read()

    try:
        lex = pygments.lexers.guess_lexer_for_filename(blob.name, data)
    except pygments.util.ClassNotFound:
        return False

    fmtr = pygments.formatters.HtmlFormatter(full=True)

    make_dirs(tgt)
    with open(tgt, "w") as f:
        pygments.highlight(data, lex, fmtr, f)

    print "Wrote", tgt, "using", lex.name

    tgt_raw = target(blob.path, raw=True)
    make_dirs(tgt_raw)
    with open(tgt_raw, "w") as f:
        f.write(data)

    return True

def traverse(tree):
    filelist = []

    for blob in tree.traverse():
        if not isinstance(blob, git.Blob):
            continue

        if skip(blob):
            print "Skipping (rule)", blob.path
            continue

        success = process(blob)

        if success:
            filelist.append(blob.path)
        else:
            print "Skipping (can't parse)", blob.path

    return filelist

def write_index(filelist):
    f = target("index")
    with open(f, "w") as f:
        f.write("<!DOCTYPE html><html>")
        f.write("<style type='text/css'>"
                "li a { font-family: monospace; }"
                "</style>")
        f.write("<body>\n")
        for n in sorted(filelist):
            # Who cares about escaping?
            t = target(n, rel=True)
            r = target(n, raw=True, rel=True)
            f.write("<li><a href='{0}'>{1}</a> "
                    "<a href='{2}'>(raw)</a></li>\n".format(t, n, r))
        f.write("</body></html>")

def main():
    repo = git.Repo("temp.git")
    filelist = traverse(repo.tree())
    write_index(filelist)

if __name__ == "__main__":
    main()
	#!/usr/bin/python

	import sys
	import copy
	import errno
	import os
	import git
	import pygments
	import pygments.lexers
	import pygments.formatters

	def skip(blob):
	# don't even consider gitignore and .pdf .odt
	if blob.name.endswith(".pdf") or blob.name.endswith(".odt"):
	return True
	if blob.name == ".gitignore":
	return True
	return False

	def target(path, rel=False, raw=False):
	assert ".." not in path
	assert not path.startswith("/") and not path.endswith("/")
	assert path
	if raw:
	path = "_raw/" + path
	if not rel:
	path = "html/" + path
	if not raw:
	path += ".html"
	return path

	def make_dirs(tgt):
	tgt_dir = os.path.dirname(tgt)
	try:
	os.makedirs(tgt_dir)
	pass
	except OSError as e:
	if e.errno == errno.EEXIST:
	pass
	else:
	raise
	else:
	print "Created directory", tgt_dir

	def process(blob):
	tgt = target(blob.path)
	data = blob.data_stream.read()

	try:
	lex = pygments.lexers.guess_lexer_for_filename(blob.name, data)
	except pygments.util.ClassNotFound:
	return False

	fmtr = pygments.formatters.HtmlFormatter(full=True)

	make_dirs(tgt)
	with open(tgt, "w") as f:
	pygments.highlight(data, lex, fmtr, f)

	print "Wrote", tgt, "using", lex.name

	tgt_raw = target(blob.path, raw=True)
	make_dirs(tgt_raw)
	with open(tgt_raw, "w") as f:
	f.write(data)

	return True

	def traverse(tree):
	filelist = []

	for blob in tree.traverse():
	if not isinstance(blob, git.Blob):
	continue

	if skip(blob):
	print "Skipping (rule)", blob.path
	continue

	success = process(blob)

	if success:
	filelist.append(blob.path)
	else:
	print "Skipping (can't parse)", blob.path

	return filelist

	def write_index(filelist):
	f = target("index")
	with open(f, "w") as f:
	f.write("<!DOCTYPE html><html>")
	f.write("<style type='text/css'>"
	"li a { font-family: monospace; }"
	"</style>")
	f.write("<body>\n")
	for n in sorted(filelist):
	# Who cares about escaping?
	t = target(n, rel=True)
	r = target(n, raw=True, rel=True)
	f.write("<li><a href='{0}'>{1}</a> "
	"<a href='{2}'>(raw)</a></li>\n".format(t, n, r))
	f.write("</body></html>")

	def main():
	repo = git.Repo("temp.git")
	filelist = traverse(repo.tree())
	write_index(filelist)

	if __name__ == "__main__":
	main()