def parse_metadata(self, sort_by_field, reverse_sort=False, header="tei"):
"""Parsing metadata fields in TEI or Dublin Core headers"""
print("### Parsing metadata ###")
print("%s: Parsing metadata in %d files..." %
(time.ctime(), len(self.list_files())))
if header == "tei":
load_metadata = self.parse_tei_header()
elif header == "dc":
load_metadata = self.parse_dc_header()
print("%s: Sorting files by the following metadata fields: %s..." %
(time.ctime(), ", ".join([i for i in sort_by_field])),
end=' ')
self.sort_order = sort_by_field # to be used for the sort by concordance biblio key in web config
if sort_by_field:
return sort_list(load_metadata, sort_by_field)
else:
sorted_load_metadata = []
for filename in self.filenames:
for m in load_metadata:
if m["filename"] == filename:
sorted_load_metadata.append(m)
break
return sorted_load_metadata
def parse_metadata(self, sort_by_field, header="tei"):
"""Parsing metadata fields in TEI or Dublin Core headers"""
print("### Parsing metadata ###", flush=True)
print(
f"{time.ctime()}: Parsing document level metadata: 0/{len(os.listdir(self.textdir))} done...",
flush=True,
end="",
)
if header == "tei":
load_metadata = self.parse_tei_header()
elif header == "dc":
load_metadata = self.parse_dc_header()
print(
f"\r{time.ctime()}: Parsing document level metadata: {len(os.listdir(self.textdir))}/{len(os.listdir(self.textdir))} done...",
flush=True,
)
print(
"%s: Sorting files by the following metadata fields: %s..." %
(time.ctime(), ", ".join([i for i in sort_by_field])),
end=" ",
flush=True,
)
self.sort_order = sort_by_field # to be used for the sort by concordance biblio key in web config
if sort_by_field:
return sort_list(load_metadata, sort_by_field)
sorted_load_metadata = []
for filename in self.filenames:
for m in load_metadata:
if m["filename"] == os.path.basename(filename):
sorted_load_metadata.append(m)
break
return sorted_load_metadata
def parse_metadata(self, sort_by_field, header="tei"):
"""Parsing metadata fields in TEI or Dublin Core headers"""
print("### Parsing metadata ###", flush=True)
print("%s: Parsing metadata in %d files..." % (time.ctime(), len(os.listdir(self.textdir))), flush=True)
if header == "tei":
load_metadata = self.parse_tei_header()
elif header == "dc":
load_metadata = self.parse_dc_header()
print(
"%s: Sorting files by the following metadata fields: %s..." % (time.ctime(), ", ".join([i for i in sort_by_field])),
end=" ",
flush=True,
)
self.sort_order = sort_by_field # to be used for the sort by concordance biblio key in web config
if sort_by_field:
return sort_list(load_metadata, sort_by_field)
sorted_load_metadata = []
for filename in self.filenames:
for m in load_metadata:
if m["filename"] == os.path.basename(filename):
sorted_load_metadata.append(m)
break
return sorted_load_metadata
def parse_metadata(self, sort_by_field, reverse_sort=False, header="tei"):
"""Parsing metadata fields in TEI or Dublin Core headers"""
print("### Parsing metadata ###", flush=True)
print("%s: Parsing metadata in %d files..." % (time.ctime(), len(os.listdir(self.textdir))), flush=True)
if header == "tei":
load_metadata = self.parse_tei_header()
elif header == "dc":
load_metadata = self.parse_dc_header()
print("%s: Sorting files by the following metadata fields: %s..." % (time.ctime(),
", ".join([i for i in sort_by_field])), end=' ', flush=True)
self.sort_order = sort_by_field # to be used for the sort by concordance biblio key in web config
if sort_by_field:
return sort_list(load_metadata, sort_by_field)
else:
return load_metadata
def get_sorted_hits(all_results, sort_keys, request, config, db, start, end):
hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
start, end, n = page_interval(request.results_per_page, hits, start, end)
kwic_object = {
"description": {"start": start,
"end": end,
"results_per_page": request.results_per_page},
"query": dict([i for i in request])
}
kwic_results = []
for index in sort_list(all_results, sort_keys)[start:end]:
hit = hits[index["index"]]
kwic_result = kwic_hit_object(hit, config, db)
kwic_results.append(kwic_result)
kwic_object['results'] = kwic_results
kwic_object['results_length'] = len(hits)
kwic_object["query_done"] = hits.done
return kwic_object
def get_sorted_hits(all_results, sort_keys, request, config, db, start, end):
hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
start, end, n = page_interval(request.results_per_page, hits, start, end)
kwic_object = {
"description": {"start": start,
"end": end,
"results_per_page": request.results_per_page},
"query": dict([i for i in request])
}
kwic_results = []
for index in sort_list(all_results, sort_keys)[start:end]:
hit = hits[index["index"]]
kwic_result = kwic_hit_object(hit, config, db)
kwic_results.append(kwic_result)
kwic_object['results'] = kwic_results
kwic_object['results_length'] = len(hits)
kwic_object["query_done"] = hits.done
return kwic_object
def parse_metadata(self, sort_by_field, reverse_sort=False, header="tei"):
"""Parsing metadata fields in TEI or Dublin Core headers"""
print("### Parsing metadata ###")
print("%s: Parsing metadata in %d files..." % (time.ctime(), len(self.list_files())))
if header == "tei":
load_metadata = self.parse_tei_header()
elif header == "dc":
load_metadata = self.parse_dc_header()
print("%s: Sorting files by the following metadata fields: %s..." % (time.ctime(),
", ".join([i for i in sort_by_field])), end=' ')
self.sort_order = sort_by_field # to be used for the sort by concordance biblio key in web config
if sort_by_field:
return sort_list(load_metadata, sort_by_field)
else:
sorted_load_metadata = []
for filename in self.filenames:
for m in load_metadata:
if m["filename"] == filename:
sorted_load_metadata.append(m)
break
return sorted_load_metadata