Merge branch 'master' of https://github.com/Phyks/BMC

Search for Digital Object Identifier as well as DOI in text.

README.md

@@ -5,6 +5,9 @@ BiblioManager is a simple script to download and store your articles. Read on if
 
 **Note :** This script is currently a work in progress.
 
+**Note: If you want to extract some functions from this repo, please consider using [libbmc](https://github.com/Phyks/libbmc/) instead, which is specifically dedicated to this (and this repo should be using it, rather than duplicating code).**
+
+
 Travis build status : [![Build Status](https://travis-ci.org/Phyks/BMC.svg?branch=master)](https://travis-ci.org/Phyks/BMC)
 
 ## What is BiblioManager (or what it is **not**) ?

libbmc/fetcher.py

@@ -22,7 +22,7 @@ try:
     from urllib.error import URLError
 except ImportError:
     # Fall back to Python 2's urllib2
-    from urllib2 import urlopen, Request
+    from urllib2 import urlopen, Request, URLError
 import arxiv2bib as arxiv_metadata
 import libbmc.tools as tools
 import bibtexparser
@@ -213,15 +213,14 @@ def findArticleID(src, only=["DOI", "arXiv"]):
         extractfull += ' '.join([i.decode(stdout_encoding).strip() for i in totext.stdout.readlines()])
         # Try to extract DOI
         if "DOI" in only:
-            extractID = doi_re.search(extractfull.lower().replace('Œ', '-'))
+            extractlower = extractfull.lower().replace('digital object identifier', 'doi')
+            extractID = doi_re.search(extractlower.replace('Œ', '-'))
             if not extractID:
                 # PNAS fix
-                extractID = doi_pnas_re.search(extractfull.
-                                               lower().
-                                               replace('pnas', '/pnas'))
+                extractID = doi_pnas_re.search(extractlower.replace('pnas', '/pnas'))
                 if not extractID:
                     # JSB fix
-                    extractID = doi_jsb_re.search(extractfull.lower())
+                    extractID = doi_jsb_re.search(extractlower)
             if extractID:
                 extract_type = "DOI"
                 totext.terminate()

libbmc/tests/src/doi.bib

@@ -8,5 +8,5 @@
 	number = {4},
 	author = {Yan-Hua Hou and Lev P. Pitaevskii and Sandro Stringari},
 	title = {First and second sound in a highly elongated Fermi gas at unitarity},
-	journal = {Physical Review A}
+	journal = {Phys. Rev. A}
 }

libbmc/tests/test_backend.py

@@ -123,7 +123,7 @@ Lattice},
 
     def test_getBibtex_id(self):
         bibtexAppend(self.bibtex_article)
-        got = getBibtex(self.bibtex_article['ID'], file_id='ID')
+        got = getBibtex(self.bibtex_article['ID'], file_id='id')
         self.assertEqual(got, self.bibtex_article)
 
     def test_getBibtex_file(self):

libbmc/tests/test_tools.py

@@ -19,7 +19,7 @@ class TestTools(unittest.TestCase):
         self.assertEqual(slugify(u"à&é_truc.pdf"), "ae_trucpdf")
 
     def test_parsed2Bibtex(self):
-        parsed = {'type': 'article', 'id': 'test', 'field1': 'test1',
+        parsed = {'ENTRYTYPE': 'article', 'ID': 'test', 'field1': 'test1',
                   'field2': 'test2'}
         expected = ('@article{test,\n\tfield1={test1},\n' +
                     '\tfield2={test2},\n}\n\n')