Rename repository and merged local changes.

I was updating the scripts in my local bin; the changes have been added
here. The test script needs to be updated.

.gitignore

@@ -1,7 +1,7 @@
 *__pycache__/
 build/
 dist/
-mybiblib.egg-info/
+bibtools.egg-info/
 *swp
 prereqs.txt
 tags

README.md

@@ -1,3 +1,6 @@
-# SearchRefs
+# bibtools
 
+A set of tools for processing a reference database composed of bib files.
 
+The package is built around the [bib file parser](https://github.com/aclements/biblib) of aclement.
+Scripts are included for three common tasks: parsing downloaded bib files, searching the database, and creating project specific bibliographies.

mybiblib/bib.py → bibtools/bib.py

@@ -32,7 +32,7 @@ def unabbreviate(self, abb):
         try:
             abb = self._abb_to_full[abb]
         except KeyError:
-            print('Abbreviation not in database for journal {}'.format(full))
+            print('Abbreviation not in database for journal {}'.format(abb))
             raise
 
         return abb
@@ -91,7 +91,8 @@ def fields_match(self, tested_fields):
             if operator in ('and', 'or'):
                 try:
                     if self._operators[operator_index + 1] == 'not':
-                        tested_fields[field_index] = not tested_fields[field_index]
+                        tested_fields[field_index] = (
+                            not tested_fields[field_index])
                     else:
                         pass
                 except IndexError:
@@ -151,15 +152,18 @@ def standarize_order_and_fields(self):
         standard = OrderedDict()
         if typ == 'article':
             fields = ['author', 'title', 'journal', 'volume', 'pages', 'year',
-                    'doi']
+                      'doi']
         elif typ == 'book':
             fields = ['author', 'title', 'year', 'publisher', 'isbn']
         elif typ == 'phdthesis':
             fields = ['author', 'title', 'year', 'school']
         elif typ == 'inproceedings':
-            fields = ['author', 'title', 'booktitle', 'series', 'year', 'isbn', 'location', 'pages', 'doi', 'publisher', 'address']
+            fields = ['author', 'title', 'booktitle', 'series', 'year',
+                      'isbn', 'location', 'pages', 'doi', 'publisher',
+                      'address']
         elif typ == 'inbook':
-            fields = ['author', 'editor', 'title', 'booktitle', 'year', 'isbn', 'pages', 'doi', 'publisher', 'address']
+            fields = ['author', 'editor', 'title', 'booktitle',
+                      'year', 'isbn', 'pages', 'doi', 'publisher', 'address']
         else:
             print('Standard not defined for entry type {}'.format(typ))
             print(key)
@@ -187,7 +191,7 @@ def unabbreviate_journal(self, abbreviations):
                 self._entry['journal'] = full
 
     def write_to_file(self, filename=None):
-        if filename == None:
+        if filename is None:
             filename = '{}.tex'.format(self._entry.key)
 
         with open(filename, 'w') as f:
@@ -199,6 +203,7 @@ def as_string(self):
 
 class Bibliography:
     """Bibliography composed of individual bib files in a directory"""
+
     def __init__(self, bib_directory):
         bibfile_names = []
         for bibfile_name in os.listdir(bib_directory):

scripts/makebib.py

@@ -5,7 +5,7 @@
 import argparse
 import re
 
-import mybiblib.bib as mbl
+import bibtools.bib as btl
 
 
 BIB_DIRECTORY = '/home/alexc/refs/bibs/'
@@ -22,13 +22,13 @@ def main():
 def parse_args():
     parser = argparse.ArgumentParser()
     parser.add_argument(
-            'latex_file',
-            type=str,
-            help='Input tex file')
+        'latex_file',
+        type=str,
+        help='Input tex file')
     parser.add_argument(
-            'bib_file',
-            type=str,
-            help='Output bib file')
+        'bib_file',
+        type=str,
+        help='Output bib file')
     return parser.parse_args()
 
 
@@ -37,7 +37,7 @@ def parse_latex_file(filename):
         latex_file = f.read()
 
     cite_commands = re.finditer(r'(cite)(t|num)?(\{)(?P<keys>[\w*,-]*)(\})',
-                               latex_file)
+                                latex_file)
     empty_citations = 0
     bib_keys = []
     for cite in cite_commands:
@@ -71,8 +71,8 @@ def empty_citation(keys):
 
 def create_bib_entries(bib_keys):
     bib_entries = []
-    bib = mbl.Bibliography(BIB_DIRECTORY)
-    abbs = mbl.Abbreviations(ABBREVS_FILE)
+    bib = btl.Bibliography(BIB_DIRECTORY)
+    abbs = btl.Abbreviations(ABBREVS_FILE)
     for bib_key in bib_keys:
         try:
             bib_entry = bib[bib_key]

scripts/parsebib.py

@@ -1,13 +1,51 @@
 #!/usr/bin/env python3
 
-"""Parse bib files and output in standard format; warn if missing information"""
+"""Parse bib files and output in standard format"""
 
 # For now assumes bib file is article
 
 import argparse
 
 
-FIELDS = ['title', 'author', 'journal', 'volume', 'number', 'pages', 'year', 'issn', 'doi', 'url', 'abstract']
+FIELDS = ['title', 'author', 'journal', 'volume', 'number',
+          'pages', 'year', 'issn', 'doi', 'url', 'abstract']
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('filebase', help='Filebase of bib file')
+    args = parser.parse_args()
+    filebase = args.filebase
+
+    filename = filebase + '.bib'
+
+    with open(filename) as inp:
+        lines = inp.readlines()
+
+    field_dic = {}
+    merged_line = ''
+    for line in lines[1:]:
+        if '@' in line:
+            continue
+        line = line.lstrip()
+        line = line.rstrip('\n')
+        if line[0] == '}':
+            continue
+        if line[-2] != '}':
+            merged_line = merged_line + line
+            continue
+        else:
+            if merged_line != '':
+                line = merged_line + line
+                merged_line = ''
+        if line == '\n':
+            continue
+        else:
+            field_dic = find_entry(line, field_dic)
+
+
+    # modify field contents (capitilization, brackets, etc.)
+    output_standard_bib(filebase, field_dic)
 
 
 def find_entry(line, field_dic):
@@ -36,28 +74,5 @@ def output_standard_bib(filebase, field_dic):
     print('}')
 
 
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('filebase', help='Filebase of bib file')
-    args = parser.parse_args()
-    filebase = args.filebase
-
-    filename = filebase + '.bib'
-
-
-    with open(filename) as inp:
-        lines = inp.readlines()
-
-    field_dic = {}
-    for line in lines[1:]:
-        if line == '\n':
-            continue
-        else:
-            field_dic = find_entry(line, field_dic)
-
-    #modify field contents (capitilization, brackets, etc.)
-    output_standard_bib(filebase, field_dic)
-
-
 if __name__ == '__main__':
     main()

scripts/searchbibs.py

@@ -3,27 +3,37 @@
 """Search bibliography database with and output given terms."""
 
 
+import argparse
+
+import bibtools.bib as btl
+
+
+BIB_DIRECTORY = '/home/alexc/refs/bibs/'
+
+
 def main():
     args = parse_args()
-    bibliography = Bibliography(BIB_DIRECTORY)
-    search_string = SearchString(args.search_string)
+    bibliography = btl.Bibliography(BIB_DIRECTORY)
+    search_string = btl.SearchString(args.search_string)
     bibliography.match_and_print_fields(search_string, args.terms)
 
 
 def parse_args():
     parser = argparse.ArgumentParser()
     parser.add_argument(
-            '-s',
-            type=str,
-            nargs='+',
-            dest='search_string',
-            help='Search string')
+        '-s',
+        type=str,
+        nargs='+',
+        dest='search_string',
+        help='Search string')
     parser.add_argument(
-            '-t',
-            type=str,
-            nargs='+',
-            dest='terms',
-            help='Terms to print')
+        '-t',
+        type=str,
+        nargs='+',
+        default=['title', 'year', 'author', 'annote'],
+        dest='terms',
+        help='Terms to print')
+
     return parser.parse_args()
 
 

setup.py

@@ -2,8 +2,8 @@
 from setuptools import setup
 
 setup(
-    name='mybiblib',
-    packages=['mybiblib'],
+    name='bibtools',
+    packages=['bibtools'],
     scripts=glob.glob('scripts/*.py'),
     install_requires=['biblib']
 )

tests/test_bib.py

@@ -1,34 +1,37 @@
 #!/usr/env python
 
-from searchRefs import *
 import pytest
 
+import bibtools as btl
+
 
 @pytest.fixture
 def search_string_simple():
-    input_list= ['field:keywords', 'stuff', 'thing']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'stuff', 'thing']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_negation():
     input_list = ['not', 'field:keywords', 'stuff', 'thing']
-    search_string = SearchString(input_list)
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_conjunction():
-    input_list= ['field:keywords', 'stuff', 'thing', 'and', 'field:author', 'pande']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'stuff',
+                  'thing', 'and', 'field:author', 'pande']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_disjunction():
-    input_list = ['field:keywords', 'stuff', 'thing', 'or', 'field:author', 'pande']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'stuff',
+                  'thing', 'or', 'field:author', 'pande']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
@@ -38,9 +41,11 @@ class TestSearchString:
         (search_string_simple(), ['keywords'], [['stuff', 'thing']]),
         (search_string_negation(), ['keywords'], [['stuff', 'thing']]),
         (search_string_conjunction(), ['keywords', 'author'], [['stuff',
-            'thing'], ['pande']]),
+                                                                'thing'],
+                                                               ['pande']]),
         (search_string_disjunction(), ['keywords', 'author'], [['stuff',
-            'thing'], ['pande']])])
+                                                                'thing'],
+                                                               ['pande']])])
     def test__iter__(self, search_string, field_list, terms_list):
         test_field_list = []
         test_terms_list = []
@@ -71,41 +76,45 @@ def test_fields_match(self, search_string, tested_fields, match):
 
 @pytest.fixture()
 def bibfile_pande():
-    bibfile_pande = BibFile('pande2010.bib')
+    bibfile_pande = btl.BibFile('pande2010.bib')
     return bibfile_pande
 
 
 @pytest.fixture
 def search_string_pande_1():
-    input_list= ['field:keywords', 'review', 'msm']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'review', 'msm']
+    search_string = btl.SearchString(input_list)
     return search_string
 
+
 @pytest.fixture
 def search_string_pande_2():
-    input_list= ['field:keywords', 'review', 'msm', 'thing']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'review', 'msm', 'thing']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_pande_3():
-    input_list= ['field:keywords', 'review', 'msm', 'and', 'field:author', 'pande']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'review',
+                  'msm', 'and', 'field:author', 'pande']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_pande_4():
-    input_list= ['field:keywords', 'review', 'msm', 'and', 'not', 'field:author', 'pande']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'review', 'msm',
+                  'and', 'not', 'field:author', 'pande']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
 @pytest.fixture
 def search_string_pande_5():
-    input_list= ['field:keywords', 'review', 'msm', 'or', 'not', 'field:author', 'pande']
-    search_string = SearchString(input_list)
+    input_list = ['field:keywords', 'review',
+                  'msm', 'or', 'not', 'field:author', 'pande']
+    search_string = btl.SearchString(input_list)
     return search_string
 
 
@@ -126,12 +135,12 @@ def test_search_string_match(self, bibfile_pande, search_string, match):
         (['annote', 'title'], ['Everything', 'Review'])])
     def test_get_field(self, bibfile_pande, fields, first_words):
         field_texts = bibfile_pande.get_field_texts(fields)
-        test_first_words = [field_text.split()[0] for field_text in field_texts]
+        test_first_words = [field_text.split()[0]
+                            for field_text in field_texts]
         assert test_first_words == first_words
 
 
 class TestBibliography:
 
     def test_match_and_print_fields(self):
         pass
-