def get_expression(
journal_name=None, text_terms=None, mesh_terms=None,
from_date=None, to_date=None, custom_expression=None,
author_name=None):
expression_parts = []
if journal_name:
expression_parts.append('"%s"[Journal]' % journal_name)
if text_terms or mesh_terms:
terms = []
terms.extend('"%s"[Text Word]' % x for x in text_terms or [])
terms.extend('"%s"[MeSH Terms]' % x for x in mesh_terms or [])
expression_parts.append(' OR '.join(terms))
if custom_expression:
expression_parts.append(custom_expression)
if author_name:
expression_parts.append('%s[Author]' % author_name)
if from_date:
from_date_string = from_date.strftime(
'%Y/%m/%d')
to_date_string = to_date.strftime(
'%Y/%m/%d') if to_date else '3000'
expression_parts.append(
'"%s"[Date - Publication] : "%s"[Date - Publication]' % (
from_date_string, to_date_string))
if len(expression_parts) <= 1:
expression = ''.join(expression_parts)
else:
expression = '(%s)' % ') AND ('.join(expression_parts)
return compact_whitespace(expression)
def get_expression(
journal_name=None, text_terms=None, mesh_terms=None,
from_date=None, to_date=None, custom_expression=None):
expression_parts = []
if journal_name:
expression_parts.append('"%s"[Journal]' % journal_name)
if text_terms or mesh_terms:
terms = []
terms.extend('"%s"[Text Word]' % x for x in text_terms or [])
terms.extend('"%s"[MeSH Terms]' % x for x in mesh_terms or [])
expression_parts.append(' OR '.join(terms))
if custom_expression:
expression_parts.append(custom_expression)
if from_date:
from_date_string = from_date.strftime(
'%Y/%m/%d')
to_date_string = to_date.strftime(
'%Y/%m/%d') if to_date else '3000'
expression_parts.append(
'"%s"[Date - Publication] : "%s"[Date - Publication]' % (
from_date_string, to_date_string))
if len(expression_parts) <= 1:
expression = ''.join(expression_parts)
else:
expression = '(%s)' % ') AND ('.join(expression_parts)
return compact_whitespace(expression)
def get_expression(journal_name=None,
text_terms=None,
mesh_terms=None,
from_date=None,
to_date=None,
custom_expression=None,
author_name=None):
"""
Retrieve expression based on inputs.
Expressions are constructed in this layout:
("%s"[Journal]) AND ("%s"[Text Word] OR
"%s"[Text Word] OR "%s"[MeSH Terms] OR
"%s"[MeSH Terms]) AND
("%s"[Date - Publication] : "%s"[Date - Publication])
"""
expression_parts = []
if journal_name:
expression_parts.append('"{0}"[Journal]'.format(journal_name))
if author_name:
match = PATTERN_AFFILIATION.search(author_name)
if match:
author_name, affiliation_string = match.groups()
affiliations = [x.strip() for x in affiliation_string.split(',')]
affiliation_expression = ' OR '.join('{0}[Affiliation]'.format(x)
for x in affiliations)
expression_parts.append('{0}[Author] AND ({1})'.format(
author_name, affiliation_expression))
else:
expression_parts.append('{0}[Author]'.format(author_name))
if custom_expression:
expression_parts.append(custom_expression)
if text_terms or mesh_terms:
terms = []
terms.extend('"{0}"[Text Word]'.format(x) for x in text_terms or [])
terms.extend('"{0}"[MeSH Terms]'.format(x) for x in mesh_terms or [])
expression_parts.append(' OR '.join(terms))
if from_date:
from_date_string = from_date.strftime('%Y/%m/%d')
to_date_string = to_date.strftime('%Y/%m/%d') if to_date else '3000'
expression_parts.append(
'"{0}"[Date - Publication] : "{1}"[Date - Publication]'.format(
from_date_string, to_date_string))
if len(expression_parts) <= 1:
expression = ''.join(expression_parts)
else:
expression = '({0})'.format(') AND ('.join(expression_parts))
return compact_whitespace(expression)
def get_expression(
journal_name=None, text_terms=None, mesh_terms=None,
from_date=None, to_date=None, custom_expression=None,
author_name=None):
"""
Retrieve expression based on inputs.
Expressions are constructed in this layout:
("%s"[Journal]) AND ("%s"[Text Word] OR
"%s"[Text Word] OR "%s"[MeSH Terms] OR
"%s"[MeSH Terms]) AND
("%s"[Date - Publication] : "%s"[Date - Publication])
"""
expression_parts = []
if journal_name:
expression_parts.append('"{0}"[Journal]'.format(journal_name))
if author_name:
match = PATTERN_AFFILIATION.search(author_name)
if match:
author_name, affiliation_string = match.groups()
affiliations = [x.strip() for x in affiliation_string.split(',')]
affiliation_expression = ' OR '.join(
'{0}[Affiliation]'.format(x) for x in affiliations)
expression_parts.append('{0}[Author] AND ({1})'.format(
author_name, affiliation_expression))
else:
expression_parts.append('{0}[Author]'.format(author_name))
if custom_expression:
expression_parts.append(custom_expression)
if text_terms or mesh_terms:
terms = []
terms.extend('"{0}"[Text Word]'.format(x) for x in text_terms or [])
terms.extend('"{0}"[MeSH Terms]'.format(x) for x in mesh_terms or [])
expression_parts.append(' OR '.join(terms))
if from_date:
from_date_string = from_date.strftime(
'%Y/%m/%d')
to_date_string = to_date.strftime(
'%Y/%m/%d') if to_date else '3000'
expression_parts.append(
'"{0}"[Date - Publication] : "{1}"[Date - Publication]'.format(
from_date_string, to_date_string))
if len(expression_parts) <= 1:
expression = ''.join(expression_parts)
else:
expression = '({0})'.format(') AND ('.join(expression_parts))
return compact_whitespace(expression)
def get_expression(journal_name=None,
text_terms=None,
mesh_terms=None,
from_date=None,
to_date=None,
custom_expression=None,
author_name=None):
"""
Retrieve expression based on inputs.
Expressions are constructed in this layout:
("%s"[Journal]) AND ("%s"[Text Word] OR
"%s"[Text Word] OR "%s"[MeSH Terms] OR
"%s"[MeSH Terms]) AND
("%s"[Date - Publication] : "%s"[Date - Publication])
"""
expression_parts = []
if journal_name:
expression_parts.append('"%s"[Journal]' % journal_name)
if author_name:
expression_parts.append('%s[Author]' % author_name)
if custom_expression:
expression_parts.append(custom_expression)
if text_terms or mesh_terms:
terms = []
terms.extend('"%s"[Text Word]' % x for x in text_terms or [])
terms.extend('"%s"[MeSH Terms]' % x for x in mesh_terms or [])
expression_parts.append(' OR '.join(terms))
if from_date:
from_date_string = from_date.strftime('%Y/%m/%d')
to_date_string = to_date.strftime('%Y/%m/%d') if to_date else '3000'
expression_parts.append(
'"%s"[Date - Publication] : "%s"[Date - Publication]' %
(from_date_string, to_date_string))
if len(expression_parts) <= 1:
expression = ''.join(expression_parts)
else:
expression = '(%s)' % ') AND ('.join(expression_parts)
return compact_whitespace(expression)
def test_compact_whitespace():
assert compact_whitespace(' x y z ') == 'x y z'
import csv
from collections import Counter
from invisibleroads_macros.disk import make_folder
from invisibleroads_macros.text import compact_whitespace
from os.path import join
from sys import argv
target_folder, text_path = argv[1:]
character_counter = Counter(compact_whitespace(open(text_path).read()))
del character_counter[' ']
target_path = join(make_folder(target_folder), 'character_count.csv')
csv_writer = csv.writer(open(target_path, 'w'))
csv_writer.writerows(character_counter.most_common())
print('character_count_table_path = ' + target_path)
def test_compact_whitespace():
assert compact_whitespace(' x y z ') == 'x y z'