def main():
try:
import argparse
except ImportError:
print "argparse is needed for commandline"
return 1
parser = argparse.ArgumentParser(description='Converts a module directory to an xhtml file and additional images')
parser.add_argument('directory')
parser.add_argument('-i', dest='module_id', help='Published Module id')
parser.add_argument('-c', dest='css_file', help='CSS File to include')# , type=argparse.FileType('r'))
parser.add_argument('-e', dest='epub_script', help='Name of XSL file that generates an epub from a dbk file (should look like "./xsl/dbk2___.xsl")')
parser.add_argument('-r', dest='reduce_quality', help='Reduce image quality', action='store_true')
parser.add_argument('-t', dest='content_type', help='The type of content being converted. One of ["module", "collection"]')
# parser.add_argument('-t', dest='temp_dir', help='Path to store temporary files to (default is a temp dir that will be removed)', nargs='?')
parser.add_argument('-o', dest='output', nargs='?') # , type=argparse.FileType('w'), default=sys.stdout)
args = parser.parse_args()
epubXsl = args.epub_script
if not epubXsl:
epubXsl = DEFAULT_DOCBOOK2XHTML_XSL
temp_dir = args.directory
p = util.Progress()
if args.content_type == 'module':
cnxml, allFiles = util.loadModule(args.directory)
dbk, newFiles = module2dbk.convert(args.module_id, cnxml, allFiles, {}, temp_dir, svg2png=True, math2svg=True, reduce_quality=args.reduce_quality)
dbk = newFiles['index.standalone.dbk']
allFiles.update(newFiles)
cover, newFiles = util.dbk2cover(etree.parse(StringIO(dbk)), allFiles, svg2pngFlag=True)
newFiles['cover.png'] = cover
elif args.content_type == 'collection':
p = util.Progress()
collxml, modulesDict, allFiles = util.loadCollection(args.directory)
dbk, newFiles = collection2dbk.convert(p, collxml, modulesDict, temp_dir, svg2png=True, math2svg=True, reduce_quality=args.reduce_quality)
allFiles.update(newFiles)
else:
print "Invalid content type. Must be one of ['module', 'collection']"
return 1
# Write out all the added files
for name in newFiles:
f = open(os.path.join(temp_dir, name), 'w')
f.write(newFiles[name])
f.close()
# Now, run the epub script
nothing = convert(etree.parse(StringIO(dbk)), temp_dir, args.css_file, epubXsl, args.output)
def convert(p, collxml, modulesDict, temp_dir, svg2png=True, math2svg=True, reduce_quality=False):
""" Convert a collxml file (and dictionary of module info) to a Docbook file and dict of filename:bytes) """
newFiles = {}
p.start(len(modulesDict), 'collxml to dbk')
paramsStr = PARAMS_XPATH(COLLXML_PARAMS(collxml))[0]
collParamsUnicode = eval(paramsStr) #json.loads(paramsStr)
collParams = {}
for key, value in collParamsUnicode.items():
collParams[key.encode('utf-8')] = value
dbk1 = transform(COLLXML2DOCBOOK_XSL, collxml)
modDbkDict = {}
# Each module can be converted in parallel
for module, (cnxml, filesDict) in modulesDict.items():
p.tick('Converting ' + module)
module_temp_dir = os.path.join(temp_dir, module)
if not os.path.exists(module_temp_dir):
os.makedirs(module_temp_dir)
modDbk, newFilesMod = module2dbk.convert(module, cnxml, filesDict, collParams, module_temp_dir, svg2png, math2svg, reduce_quality)
modDbkDict[module] = etree.parse(StringIO(modDbk)).getroot()
# Add newFiles with the module prefix
for f, data in newFilesMod.items():
newFiles[os.path.join(module, f)] = data
# Combine into a single large file
# Replacing Xpath xinclude magic with explicit pyhton code
for i, module in enumerate(XINCLUDE_XPATH(dbk1)):
# m9003/index.included.dbk
id = module.get('href').split('/')[0]
if id in modDbkDict:
module.getparent().replace(module, modDbkDict[id])
else:
print >> sys.stderr, "ERROR: Didn't find module source!!!!"
# Clean up image paths
dbk2 = transform(DOCBOOK_NORMALIZE_PATHS_XSL, dbk1)
dbk3 = transform(DOCBOOK_CLEANUP_XSL, dbk2)
dbk4 = transform(DOCBOOK_NORMALIZE_GLOSSARY_XSL, dbk3)
# Create cover SVG and convert it to an image
cover, newFiles2 = util.dbk2cover(dbk4, filesDict, svg2png)
if svg2png:
newFiles['cover.png'] = cover
p.finish()
return dbk4, newFiles
def convert(p, collxml, modulesDict, temp_dir, svg2png=True, math2svg=True, reduce_quality=False):
""" Convert a collxml file (and dictionary of module info) to a Docbook file and dict of filename:bytes) """
newFiles = {}
p.start(len(modulesDict), 'collxml to dbk')
paramsStr = PARAMS_XPATH(COLLXML_PARAMS(collxml))[0]
collParamsUnicode = eval(paramsStr) #json.loads(paramsStr)
collParams = {}
for key, value in collParamsUnicode.items():
collParams[key.encode('utf-8')] = value
dbk1 = transform(COLLXML2DOCBOOK_XSL, collxml)
modDbkDict = {}
# Each module can be converted in parallel
for module, (cnxml, filesDict) in modulesDict.items():
p.tick('Converting ' + module)
module_temp_dir = os.path.join(temp_dir, module)
if not os.path.exists(module_temp_dir):
os.makedirs(module_temp_dir)
modDbk, newFilesMod = module2dbk.convert(module, cnxml, filesDict, collParams, module_temp_dir, svg2png, math2svg, reduce_quality)
modDbkDict[module] = etree.parse(StringIO(modDbk)).getroot()
# Add newFiles with the module prefix
for f, data in newFilesMod.items():
newFiles[os.path.join(module, f)] = data
# Combine into a single large file
# Replacing Xpath xinclude magic with explicit pyhton code
for i, module in enumerate(XINCLUDE_XPATH(dbk1)):
# m9003/index.included.dbk
id = module.get('href').split('/')[0]
if id in modDbkDict:
module.getparent().replace(module, modDbkDict[id])
else:
print >> sys.stderr, "ERROR: Didn't find module source!!!!"
# Clean up image paths
dbk2 = transform(DOCBOOK_NORMALIZE_PATHS_XSL, dbk1)
dbk3 = transform(DOCBOOK_CLEANUP_XSL, dbk2)
dbk4 = transform(DOCBOOK_NORMALIZE_GLOSSARY_XSL, dbk3)
# Create cover SVG and convert it to an image
cover, newFiles2 = util.dbk2cover(dbk4, filesDict, svg2png)
if svg2png:
newFiles['cover.png'] = cover
p.finish()
return dbk4, newFiles
def main():
try:
import argparse
except ImportError:
print "argparse is needed for commandline"
return 1
parser = argparse.ArgumentParser(
description=
'Converts a module directory to an xhtml file and additional images')
parser.add_argument('directory')
parser.add_argument('-i', dest='module_id', help='Published Module id')
parser.add_argument(
'-c', dest='css_file',
help='CSS File to include') # , type=argparse.FileType('r'))
parser.add_argument(
'-e',
dest='epub_script',
help=
'Name of XSL file that generates an epub from a dbk file (should look like "./xsl/dbk2___.xsl")'
)
parser.add_argument('-r',
dest='reduce_quality',
help='Reduce image quality',
action='store_true')
parser.add_argument(
'-t',
dest='content_type',
help=
'The type of content being converted. One of ["module", "collection"]')
# parser.add_argument('-t', dest='temp_dir', help='Path to store temporary files to (default is a temp dir that will be removed)', nargs='?')
parser.add_argument(
'-o', dest='output',
nargs='?') # , type=argparse.FileType('w'), default=sys.stdout)
args = parser.parse_args()
epubXsl = args.epub_script
if not epubXsl:
epubXsl = DEFAULT_DOCBOOK2XHTML_XSL
temp_dir = args.directory
p = util.Progress()
if args.content_type == 'module':
cnxml, allFiles = util.loadModule(args.directory)
dbk, newFiles = module2dbk.convert(args.module_id,
cnxml,
allFiles, {},
temp_dir,
svg2png=True,
math2svg=True,
reduce_quality=args.reduce_quality)
dbk = newFiles['index.standalone.dbk']
allFiles.update(newFiles)
cover, newFiles = util.dbk2cover(etree.parse(StringIO(dbk)),
allFiles,
svg2pngFlag=True)
newFiles['cover.png'] = cover
elif args.content_type == 'collection':
p = util.Progress()
collxml, modulesDict, allFiles = util.loadCollection(args.directory)
dbk, newFiles = collection2dbk.convert(
p,
collxml,
modulesDict,
temp_dir,
svg2png=True,
math2svg=True,
reduce_quality=args.reduce_quality)
allFiles.update(newFiles)
else:
print "Invalid content type. Must be one of ['module', 'collection']"
return 1
# Write out all the added files
for name in newFiles:
f = open(os.path.join(temp_dir, name), 'w')
f.write(newFiles[name])
f.close()
# Now, run the epub script
nothing = convert(etree.parse(StringIO(dbk)), temp_dir, args.css_file,
epubXsl, args.output)