def colloc_concordance(hit, path, q, context_size):
conc_text = fetch_concordance(hit, path, context_size)
collocate = q['collocate'].decode('utf-8', 'ignore')
collocate_match = re.compile(r'(.*\W)(%s)(\W.*)' % collocate,
flags=re.U | re.I)
conc_text = collocate_match.sub(r'\1<span class="collocate">\2</span>\3',
conc_text)
return conc_text
def colloc_concordance(hit, path, q, db):
conc_text = fetch_concordance(hit, path, q)
split_text = token_regex.split(conc_text)
keep_text = []
for w in split_text:
if w:
if w.lower() == q['collocate'].decode('utf-8', 'ignore'):
w = '<span class="collocate">%s</span>' % w
keep_text.append(w)
conc_text = ''.join(keep_text)
return conc_text
def filter_words_by_property(hits, path, q, db, config, word_filter=True, filter_num=100, stopwords=True):
concordance_object = {"query": dict([i for i in q])}
length = config['concordance_length']
# Do these need to be captured in wsgi_handler?
word_property = q["word_property"]
word_property_value = q["word_property_value"]
word_property_total = q["word_property_total"]
new_hitlist = []
results = []
position = 0
more_pages = False
if q.start == 0:
start = 1
else:
start = q.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 = concordance_citation(hit, citation_hrefs)
context = fetch_concordance(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) == (q.results_per_page):
more_pages = True
break
end = start + len(results) - 1
if len(results) < q.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": q.results_per_page, "more_pages": more_pages}
print >> sys.stderr, "DONE"
return concordance_object
import os
import re
import sys
sys.path.append('..')
from functions.wsgi_handler import parse_cgi
from reports.concordance import fetch_concordance
from reports.theme_rheme import adjust_results
import cgi
import json
from philologic.DB import DB
if __name__ == "__main__":
environ = os.environ
path = environ['SCRIPT_FILENAME']
path = re.sub('(philo4/[^/]+/).*', '\\1', path)
form = cgi.FieldStorage()
num = int(form.getvalue('hit_num'))
length = int(form.getvalue('length'))
db, path_components, q = parse_cgi(environ)
hits = db.query(q["q"],q["method"],q["arg"],**q["metadata"])
if q['report'] != 'theme_rheme':
conc_text = fetch_concordance(hits[num], path, q, length=length)
else:
new_hits, full_report = adjust_results(hits, path, q, length=length)
conc_text = new_hits[num].concordance
print "Content-Type: text/html\n"
print conc_text.encode('utf-8', 'ignore')
def colloc_concordance(hit, path, q, context_size):
conc_text = fetch_concordance(hit, path, context_size)
collocate = q['collocate'].decode('utf-8', 'ignore')
collocate_match = re.compile(r'(.*\W)(%s)(\W.*)' % collocate, flags=re.U|re.I)
conc_text = collocate_match.sub(r'\1<span class="collocate">\2</span>\3', conc_text)
return conc_text
#!/usr/bin/env python
import os
import re
import sys
sys.path.append('..')
from functions.wsgi_handler import parse_cgi
from reports.concordance import fetch_concordance
from reports.theme_rheme import adjust_results
import cgi
import json
from philologic.DB import DB
if __name__ == "__main__":
environ = os.environ
path = environ['SCRIPT_FILENAME']
path = re.sub('(philo4/[^/]+/).*', '\\1', path)
form = cgi.FieldStorage()
num = int(form.getvalue('hit_num'))
length = int(form.getvalue('length'))
db, path_components, q = parse_cgi(environ)
hits = db.query(q["q"], q["method"], q["arg"], **q["metadata"])
if q['report'] != 'theme_rheme':
conc_text = fetch_concordance(hits[num], path, q, length=length)
else:
new_hits, full_report = adjust_results(hits, path, q, length=length)
conc_text = new_hits[num].concordance
print "Content-Type: text/html\n"
print conc_text.encode('utf-8', 'ignore')
