def get_pdf_snippets(recID, patterns, user_info):
"""
Extract text snippets around 'patterns' from the newest PDF file of 'recID'
The search is case-insensitive.
The snippets are meant to look like in the results of the popular search
engine: using " ... " between snippets.
For empty patterns it returns ""
@param recID: record ID to consider
@param patterns: list of patterns to retrieve
@param nb_words_around: max number of words around the matched pattern
@param max_snippets: max number of snippets to include
@return: snippet
"""
from invenio.bibdocfile import BibRecDocs, check_bibdoc_authorization
text_path = ""
text_path_courtesy = ""
for bd in BibRecDocs(recID).list_bibdocs():
# Show excluded fulltext in snippets on Inspire, otherwise depending on authorization
if bd.get_text() and (CFG_INSPIRE_SITE or not check_bibdoc_authorization(user_info, bd.get_status())[0]):
text_path = bd.get_text_path()
text_path_courtesy = bd.get_status()
if CFG_INSPIRE_SITE and not text_path_courtesy:
# get courtesy from doctype, since docstatus was empty:
text_path_courtesy = bd.get_type()
if text_path_courtesy == 'INSPIRE-PUBLIC':
# but ignore 'INSPIRE-PUBLIC' doctype
text_path_courtesy = ''
break # stop at the first good PDF textable file
nb_chars = CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.get('', 0)
max_snippets = CFG_WEBSEARCH_FULLTEXT_SNIPPETS.get('', 0)
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.has_key(text_path_courtesy):
nb_chars=CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS[text_path_courtesy]
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS.has_key(text_path_courtesy):
max_snippets=CFG_WEBSEARCH_FULLTEXT_SNIPPETS[text_path_courtesy]
if text_path and nb_chars and max_snippets:
out = ''
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS_GENERATOR == 'native':
out = get_text_snippets(text_path, patterns, nb_chars, max_snippets)
if not out:
# no hit, so check stemmed versions:
from invenio.bibindex_engine_stemmer import stem
stemmed_patterns = [stem(p, 'en') for p in patterns]
out = get_text_snippets(text_path, stemmed_patterns, nb_chars, max_snippets)
elif CFG_WEBSEARCH_FULLTEXT_SNIPPETS_GENERATOR == 'SOLR':
out = solr_get_snippet(patterns, recID, nb_chars, max_snippets)
if out:
out_courtesy = ""
if CFG_INSPIRE_SITE and text_path_courtesy:
out_courtesy = '<strong>Snippets courtesy of ' + text_path_courtesy + '</strong><br>'
return """<div class="snippetbox">%s%s</div>""" % (out_courtesy, out)
else:
return ""
else:
return ""
def get_pdf_snippets(recID, patterns, user_info):
"""
Extract text snippets around 'patterns' from the newest PDF file of 'recID'
The search is case-insensitive.
The snippets are meant to look like in the results of the popular search
engine: using " ... " between snippets.
For empty patterns it returns ""
@param recID: record ID to consider
@param patterns: list of patterns to retrieve
@param nb_words_around: max number of words around the matched pattern
@param max_snippets: max number of snippets to include
@return: snippet
"""
from invenio.bibdocfile import BibRecDocs, check_bibdoc_authorization
text_path = ""
text_path_courtesy = ""
for bd in BibRecDocs(recID).list_bibdocs():
# Show excluded fulltext in snippets on Inspire, otherwise depending on authorization
if bd.get_text() and (CFG_INSPIRE_SITE or not check_bibdoc_authorization(user_info, bd.get_status())[0]):
text_path = bd.get_text_path()
text_path_courtesy = bd.get_status()
if CFG_INSPIRE_SITE and not text_path_courtesy:
# get courtesy from doctype, since docstatus was empty:
text_path_courtesy = bd.get_type()
if text_path_courtesy == 'INSPIRE-PUBLIC':
# but ignore 'INSPIRE-PUBLIC' doctype
text_path_courtesy = ''
break # stop at the first good PDF textable file
nb_chars = CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.get('', 0)
max_snippets = CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.get('', 0)
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.has_key(text_path_courtesy):
nb_chars=CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS[text_path_courtesy]
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS.has_key(text_path_courtesy):
max_snippets=CFG_WEBSEARCH_FULLTEXT_SNIPPETS[text_path_courtesy]
if text_path and nb_chars and max_snippets:
out = ''
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS_GENERATOR == 'native':
out = get_text_snippets(text_path, patterns, nb_chars, max_snippets)
if not out:
# no hit, so check stemmed versions:
from invenio.bibindex_engine_stemmer import stem
stemmed_patterns = [stem(p, 'en') for p in patterns]
out = get_text_snippets(text_path, stemmed_patterns, nb_chars, max_snippets)
elif CFG_WEBSEARCH_FULLTEXT_SNIPPETS_GENERATOR == 'SOLR':
out = solr_get_snippet(patterns, recID, nb_chars, max_snippets)
if out:
out_courtesy = ""
if CFG_INSPIRE_SITE and text_path_courtesy:
out_courtesy = '<strong>Snippets courtesy of ' + text_path_courtesy + '</strong><br>'
return """<div class="snippetbox">%s%s</div>""" % (out_courtesy, out)
else:
return ""
else:
return ""
def template_context_function(id_bibrec, pattern, qid):
"""
@param id_bibrec ID of record
@param pattern search pattern
@param current_user user object
@param qid query id
@return HTML containing snippet
"""
if not pattern: pattern = get_pattern_from_cache(qid)
nb_chars = CFG_WEBSEARCH_FULLTEXT_SNIPPETS_CHARS.get('', 0)
max_snippets = CFG_WEBSEARCH_FULLTEXT_SNIPPETS.get('', 0)
if id_bibrec and pattern:
if CFG_WEBSEARCH_FULLTEXT_SNIPPETS and 'fulltext:' in pattern:
terms = get_fulltext_terms_from_search_pattern(pattern)
if terms:
snippets = ''
try:
snippets = solr_get_snippet(terms, id_bibrec, nb_chars,
max_snippets).decode('utf8')
if snippets: return ' ... ' + snippets + ' ... '
except:
register_exception()
return ''
else:
return ''
else:
return None