def main():
p = args_parser('catalog source files and create source.tsv')
p.add_argument('-s', '--source', default=None, help='ExternalSource')
args = get_args(parser=p)
info("importing from %s" % args.source)
outf = open_output()
sources = []
for input_source in args.inputs:
for fn, contents, dt in find_files_with_time(input_source):
if len(contents) == 0:
info("ignoring empty file")
continue
outf.write_file(strip_toplevel(fn), contents, dt)
sources.append(xd_sources_row(fn, args.source or input_source, iso8601(dt)))
info("%s files cataloged" % len(sources))
outbase = parse_pathname(args.output).base
outf.write_file("%s.tsv" % outbase, xd_sources_header + "".join(sources))
outf.write_file("%s.log" % outbase, get_log())
def main():
args = get_args('aggregates all .log files into one .html')
outwww = open_output()
log_html = ''
for fn, contents, dt in sorted(find_files_with_time(*args.inputs, ext=".log"), key=lambda x: x[2]): # earliest first
log_html += '\n\n<h2>%s</h2><pre>%s</pre>' % (fn, cgi.escape(contents.decode("utf-8")))
datestr = iso8601()
outwww.write_html("logs.html", log_html, title="logs for " + datestr)
def main():
args = get_args('aggregates all .log files')
outf = open_output()
s3 = boto3.resource('s3')
s3path = "logs/"
# bucket = conn.get_bucket(s3path)
bucket = s3.Bucket(os.environ['DOMAIN'])
for obj in sorted(bucket.objects.all(), key=lambda x: x.last_modified):
# last_modified
if s3path in obj.key:
print("Name: %s LastModified:%s" % (obj.key.encode('utf-8'), obj.last_modified))
for fn, contents, dt in sorted(find_files_with_time(*args.inputs, ext=".log"), key=lambda x: x[2]): # earliest first
outf.write_file(fn, contents.decode("utf-8"))
def main():
args = get_args('aggregates all .log files')
outf = open_output()
s3 = boto3.resource('s3')
s3path = "logs/"
# bucket = conn.get_bucket(s3path)
bucket = s3.Bucket(os.environ['DOMAIN'])
for obj in sorted(bucket.objects.all(), key=lambda x: x.last_modified):
# last_modified
if s3path in obj.key:
print("Name: %s LastModified:%s" %
(obj.key.encode('utf-8'), obj.last_modified))
for fn, contents, dt in sorted(find_files_with_time(*args.inputs,
ext=".log"),
key=lambda x: x[2]): # earliest first
outf.write_file(fn, contents.decode("utf-8"))
def main():
global args
parsers = {
'.xml': [parse_ccxml, parse_uxml],
'.json': [parse_ujson],
'.puz': [parse_puz],
'.html': [parse_xwordinfo],
'.pdf': [],
'.jpg': [],
'.gif': [],
'.xd': [], # special case, just copy the input, in case re-emitting screws it up
}
p = args_parser('convert crosswords to .xd format')
p.add_argument('--copyright', default=None, help='Default value for unspecified Copyright headers')
p.add_argument('--extsrc', default=None, help='Value for receipts.ExternalSource')
p.add_argument('--intsrc', default=None, help='Value for receipts.InternalSource')
p.add_argument('--pubid', default=None, help='PublicationAbbr (pubid) to use')
args = get_args(parser=p)
outf = open_output()
for input_source in args.inputs:
try:
# collect 'sources' metadata
source_files = {}
# collect receipts
receipts = []
for fn, contents, dt in find_files_with_time(input_source, ext='.tsv'):
progress(fn)
for row in parse_tsv_data(contents.decode('utf-8'), "Source"):
innerfn = strip_toplevel(row.SourceFilename)
if innerfn in source_files:
warn("%s: already in source_files!" % innerfn)
continue
source_files[innerfn] = row
# enumerate all files in this source, reverse-sorted by time
# (so most recent edition gets main slot in case of shelving
# conflict)
for fn, contents, dt in sorted(find_files_with_time(input_source, strip_toplevel=False), reverse=True, key=lambda x: x[2]):
if fn.endswith(".tsv") or fn.endswith(".log"):
continue
if not contents: # 0-length files
continue
innerfn = strip_toplevel(fn)
if innerfn in source_files:
srcrow = source_files[innerfn]
CaptureTime = srcrow.DownloadTime
ExternalSource = args.extsrc or srcrow.ExternalSource
SourceFilename = innerfn
else:
debug("%s not in sources.tsv" % innerfn)
CaptureTime = iso8601(dt)
ExternalSource = args.extsrc or parse_pathname(input_source).filename
SourceFilename = innerfn
ReceivedTime = iso8601(time.time())
InternalSource = args.intsrc or parse_pathname(input_source).filename
already_received = metadb.check_already_received(ExternalSource, SourceFilename)
xdid = ""
prev_xdid = "" # unshelved by default
existing_xdids = set(r.xdid for r in already_received)
if existing_xdids:
if len(existing_xdids) > 1:
warn('previously received this same file under multiple xdids:' + ' '.join(existing_xdids))
else:
prev_xdid = existing_xdids.pop()
debug('already received as %s' % prev_xdid)
# try each parser by extension
ext = parse_pathname(fn).ext.lower()
possible_parsers = parsers.get(ext, parsers[".puz"])
progress(fn)
if ext == ".xd":
outf.write_file(fn, contents.decode('utf-8'), dt)
elif not possible_parsers:
rejected = "no parser"
else:
rejected = ""
for parsefunc in possible_parsers:
try:
try:
xd = parsefunc(contents, fn)
except IncompletePuzzleParse as e:
error("%s %s" % (fn, e))
xd = e.xd
if not xd:
continue
xd.filename = replace_ext(strip_toplevel(fn), ".xd")
if not xd.get_header("Copyright"):
if args.copyright:
xd.set_header("Copyright", args.copyright)
catalog.deduce_set_seqnum(xd)
xdstr = xd.to_unicode()
mdtext = "|".join((ExternalSource,InternalSource,SourceFilename))
xdid = prev_xdid or catalog.deduce_xdid(xd, mdtext)
path = catalog.get_shelf_path(xd, args.pubid, mdtext)
outf.write_file(path + ".xd", xdstr, dt)
rejected = ""
break # stop after first successful parsing
except xdfile.NoShelfError as e:
error("could not shelve: %s" % str(e))
rejected += "[shelver] %s " % str(e)
except Exception as e:
error("%s could not convert [%s]: %s" % (parsefunc.__name__, fn, str(e)))
rejected += "[%s] %s " % (parsefunc.__name__, str(e))
# raise
if rejected:
error("could not convert: %s" % rejected)
# only add receipt if first time converting this source
if already_received:
debug("already received %s:%s" % (ExternalSource, SourceFilename))
else:
receipts.append([
CaptureTime,
ReceivedTime,
ExternalSource,
InternalSource,
SourceFilename,
xdid
])
for r in receipts:
metadb.append_row('gxd/receipts', r)
except Exception as e:
error(str(e))
if args.debug:
raise
def main():
global args
parsers = {
'.xml': [parse_ccxml, parse_uxml],
'.json': [parse_ujson],
'.puz': [parse_puz],
'.html': [parse_xwordinfo],
'.pdf': [],
'.jpg': [],
'.gif': [],
'.xd':
[], # special case, just copy the input, in case re-emitting screws it up
}
p = args_parser('convert crosswords to .xd format')
p.add_argument('--copyright',
default=None,
help='Default value for unspecified Copyright headers')
p.add_argument('--extsrc',
default=None,
help='Value for receipts.ExternalSource')
p.add_argument('--intsrc',
default=None,
help='Value for receipts.InternalSource')
p.add_argument('--pubid',
default=None,
help='PublicationAbbr (pubid) to use')
args = get_args(parser=p)
outf = open_output()
for input_source in args.inputs:
try:
# collect 'sources' metadata
source_files = {}
# collect receipts
receipts = []
for fn, contents, dt in find_files_with_time(input_source,
ext='.tsv'):
progress(fn)
for row in parse_tsv_data(contents.decode('utf-8'), "Source"):
innerfn = strip_toplevel(row.SourceFilename)
if innerfn in source_files:
warn("%s: already in source_files!" % innerfn)
continue
source_files[innerfn] = row
# enumerate all files in this source, reverse-sorted by time
# (so most recent edition gets main slot in case of shelving
# conflict)
for fn, contents, dt in sorted(find_files_with_time(
input_source, strip_toplevel=False),
reverse=True,
key=lambda x: x[2]):
if fn.endswith(".tsv") or fn.endswith(".log"):
continue
if not contents: # 0-length files
continue
innerfn = strip_toplevel(fn)
if innerfn in source_files:
srcrow = source_files[innerfn]
CaptureTime = srcrow.DownloadTime
ExternalSource = args.extsrc or srcrow.ExternalSource
SourceFilename = innerfn
else:
debug("%s not in sources.tsv" % innerfn)
CaptureTime = iso8601(dt)
ExternalSource = args.extsrc or parse_pathname(
input_source).filename
SourceFilename = innerfn
ReceivedTime = iso8601(time.time())
InternalSource = args.intsrc or parse_pathname(
input_source).filename
already_received = metadb.check_already_received(
ExternalSource, SourceFilename)
xdid = ""
prev_xdid = "" # unshelved by default
existing_xdids = set(r.xdid for r in already_received)
if existing_xdids:
if len(existing_xdids) > 1:
warn(
'previously received this same file under multiple xdids:'
+ ' '.join(existing_xdids))
else:
prev_xdid = existing_xdids.pop()
debug('already received as %s' % prev_xdid)
# try each parser by extension
ext = parse_pathname(fn).ext.lower()
possible_parsers = parsers.get(ext, parsers[".puz"])
progress(fn)
if ext == ".xd":
outf.write_file(fn, contents.decode('utf-8'), dt)
elif not possible_parsers:
rejected = "no parser"
else:
rejected = ""
for parsefunc in possible_parsers:
try:
try:
xd = parsefunc(contents, fn)
except IncompletePuzzleParse as e:
error("%s %s" % (fn, e))
xd = e.xd
if not xd:
continue
xd.filename = replace_ext(strip_toplevel(fn),
".xd")
if not xd.get_header("Copyright"):
if args.copyright:
xd.set_header("Copyright", args.copyright)
catalog.deduce_set_seqnum(xd)
xdstr = xd.to_unicode()
mdtext = "|".join((ExternalSource, InternalSource,
SourceFilename))
xdid = prev_xdid or catalog.deduce_xdid(xd, mdtext)
path = catalog.get_shelf_path(
xd, args.pubid, mdtext)
outf.write_file(path + ".xd", xdstr, dt)
rejected = ""
break # stop after first successful parsing
except xdfile.NoShelfError as e:
error("could not shelve: %s" % str(e))
rejected += "[shelver] %s " % str(e)
except Exception as e:
error("%s could not convert [%s]: %s" %
(parsefunc.__name__, fn, str(e)))
rejected += "[%s] %s " % (parsefunc.__name__,
str(e))
# raise
if rejected:
error("could not convert: %s" % rejected)
# only add receipt if first time converting this source
if already_received:
debug("already received %s:%s" %
(ExternalSource, SourceFilename))
else:
receipts.append([
CaptureTime, ReceivedTime, ExternalSource,
InternalSource, SourceFilename, xdid
])
for r in receipts:
metadb.append_row('gxd/receipts', r)
except Exception as e:
error(str(e))
if args.debug:
raise