def concordance_results(request, config):
"""Fetch concordances results."""
db = DB(config.db_path + '/data/')
if request.collocation_type:
first_hits = db.query(request["q"], request["method"], request["arg"],
**request.metadata)
second_hits = db.query(request["left"], request["method"],
request["arg"], **request.metadata)
hits = CombinedHitlist(first_hits, second_hits)
else:
hits = db.query(request["q"],
request["method"],
request["arg"],
sort_order=request["sort_order"],
**request.metadata)
start, end, page_num = page_interval(request['results_per_page'], hits,
request.start, request.end)
concordance_object = {
"description": {
"start": start,
"end": end,
"results_per_page": request.results_per_page
},
"query": dict([i for i in request]),
"default_object": db.locals['default_object_level']
}
formatting_regexes = []
if config.concordance_formatting_regex:
for pattern, replacement in config.concordance_formatting_regex:
compiled_regex = re.compile(r'%s' % pattern)
formatting_regexes.append((compiled_regex, replacement))
results = []
for hit in hits[start - 1:end]:
citation_hrefs = citation_links(db, config, hit)
metadata_fields = {}
for metadata in db.locals['metadata_fields']:
metadata_fields[metadata] = hit[metadata]
citation = citations(hit, citation_hrefs, config, report="concordance")
context = get_concordance_text(db, hit, config.db_path,
config.concordance_length)
if formatting_regexes:
for formatting_regex, replacement in formatting_regexes:
context = formatting_regex.sub(r'%s' % replacement, context)
result_obj = {
"philo_id": hit.philo_id,
"citation": citation,
"citation_links": citation_hrefs,
"context": context,
"metadata_fields": metadata_fields,
"bytes": hit.bytes
}
results.append(result_obj)
concordance_object["results"] = results
concordance_object['results_length'] = len(hits)
concordance_object["query_done"] = hits.done
return concordance_object
def concordance_results(request, config):
"""Fetch concordances results."""
db = DB(config.db_path + '/data/')
if request.collocation_type:
first_hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
second_hits = db.query(request["left"], request["method"], request["arg"], **request.metadata)
hits = CombinedHitlist(first_hits, second_hits)
else:
hits = db.query(request["q"],
request["method"],
request["arg"],
sort_order=request["sort_order"],
**request.metadata)
start, end, page_num = page_interval(request['results_per_page'], hits, request.start, request.end)
concordance_object = {
"description": {"start": start,
"end": end,
"results_per_page": request.results_per_page},
"query": dict([i for i in request]),
"default_object": db.locals['default_object_level']
}
formatting_regexes = []
if config.concordance_formatting_regex:
for pattern, replacement in config.concordance_formatting_regex:
compiled_regex = re.compile(r'%s' % pattern)
formatting_regexes.append((compiled_regex, replacement))
results = []
for hit in hits[start - 1:end]:
citation_hrefs = citation_links(db, config, hit)
metadata_fields = {}
for metadata in db.locals['metadata_fields']:
metadata_fields[metadata] = hit[metadata]
citation = citations(hit, citation_hrefs, config, report="concordance")
context = get_concordance_text(db, hit, config.db_path, config.concordance_length)
if formatting_regexes:
for formatting_regex, replacement in formatting_regexes:
context = formatting_regex.sub(r'%s' % replacement, context)
result_obj = {
"philo_id": hit.philo_id,
"citation": citation,
"citation_links": citation_hrefs,
"context": context,
"metadata_fields": metadata_fields,
"bytes": hit.bytes
}
results.append(result_obj)
concordance_object["results"] = results
concordance_object['results_length'] = len(hits)
concordance_object["query_done"] = hits.done
return concordance_object
def filter_words_by_property(request, config):
"""Filter words by property"""
db = DB(config.db_path + '/data/')
hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
concordance_object = {"query": dict([i for i in request])}
# Do these need to be captured in wsgi_handler?
word_property = request["word_property"]
word_property_value = request["word_property_value"]
word_property_total = request["word_property_total"]
new_hitlist = []
results = []
position = 0
more_pages = False
if request.start == 0:
start = 1
else:
start = request.start
for hit in hits:
# get my chunk of text
hit_val = get_word_attrib(hit, word_property, db)
if hit_val == word_property_value:
position += 1
if position < start:
continue
new_hitlist.append(hit)
citation_hrefs = citation_links(db, config, hit)
metadata_fields = {}
for metadata in db.locals['metadata_fields']:
metadata_fields[metadata] = hit[metadata]
citation = citations(hit, citation_hrefs, config)
context = get_concordance_text(db, hit, config.db_path, config.concordance_length)
result_obj = {
"philo_id": hit.philo_id,
"citation": citation,
"citation_links": citation_hrefs,
"context": context,
"metadata_fields": metadata_fields,
"bytes": hit.bytes,
"collocate_count": 1
}
results.append(result_obj)
if len(new_hitlist) == (request.results_per_page):
more_pages = True
break
end = start + len(results) - 1
if len(results) < request.results_per_page:
word_property_total = end
else:
word_property_total = end + 1
concordance_object['results'] = results
concordance_object["query_done"] = hits.done
concordance_object['results_length'] = word_property_total
concordance_object["description"] = {
"start": start,
"end": end,
"results_per_page": request.results_per_page,
"more_pages": more_pages
}
return concordance_object
def filter_words_by_property(request, config):
"""Filter words by property"""
db = DB(config.db_path + "/data/")
hits = db.query(request["q"], request["method"], request["arg"], **request.metadata)
concordance_object = {"query": dict([i for i in request])}
# Do these need to be captured in wsgi_handler?
word_property = request["word_property"]
word_property_value = request["word_property_value"]
word_property_total = request["word_property_total"]
new_hitlist = []
results = []
position = 0
more_pages = False
if request.start == 0:
start = 1
else:
start = request.start
for hit in hits:
# get my chunk of text
hit_val = get_word_attrib(hit, word_property, db)
if hit_val == word_property_value:
position += 1
if position < start:
continue
new_hitlist.append(hit)
citation_hrefs = citation_links(db, config, hit)
metadata_fields = {}
for metadata in db.locals["metadata_fields"]:
metadata_fields[metadata] = hit[metadata]
citation = citations(hit, citation_hrefs, config)
context = get_concordance_text(db, hit, config.db_path, config.concordance_length)
result_obj = {
"philo_id": hit.philo_id,
"citation": citation,
"citation_links": citation_hrefs,
"context": context,
"metadata_fields": metadata_fields,
"bytes": hit.bytes,
"collocate_count": 1,
}
results.append(result_obj)
if len(new_hitlist) == (request.results_per_page):
more_pages = True
break
end = start + len(results) - 1
if len(results) < request.results_per_page:
word_property_total = end
else:
word_property_total = end + 1
concordance_object["results"] = results
concordance_object["query_done"] = hits.done
concordance_object["results_length"] = word_property_total
concordance_object["description"] = {
"start": start,
"end": end,
"results_per_page": request.results_per_page,
"more_pages": more_pages,
}
return concordance_object
