From 91685bc46b185adaa5d0ad12edbad816ced6a028 Mon Sep 17 00:00:00 2001
From: Phyks <webmaster@phyks.me>
Date: Tue, 29 Apr 2014 21:55:35 +0200
Subject: [PATCH] Various re.compile

---
 README.md  |  2 --
 fetcher.py | 32 +++++++++++++++++++++-----------
 2 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/README.md b/README.md
index 05553b9..4f2053d 100644
--- a/README.md
+++ b/README.md
@@ -108,8 +108,6 @@ A list of ideas and TODO. Don't hesitate to give feedback on the ones you really
 10. Refactor
     11. Use bibtex-parser lib to write bibtex, instead of parsed2BibTex
     12. Rebuild function
-    13. Split main.py
-    14. Various re.compile ?
     15. Check output of subprocesses before it ends
     16. TODO in files
 20. No DOI for arXiv / HAL
diff --git a/fetcher.py b/fetcher.py
index 2f1276b..297a6c7 100644
--- a/fetcher.py
+++ b/fetcher.py
@@ -40,6 +40,9 @@ def download(url):
     return False
 
 
+isbn_re = re.compile(r"isbn (([0-9]{3}[ -])?[0-9][ -][0-9]{2}[ -][0-9]{6}[-][0-9])")
+
+
 def findISBN(src):
     """Search for a valid ISBN in src.
 
@@ -59,8 +62,7 @@ def findISBN(src):
         tools.warning(extractfull[1])
         return False
     extractfull = extractfull[0]
-    extractISBN = re.search(r"isbn (([0-9]{3}[ -])?[0-9][ -][0-9]{2}[ -][0-9]{6}[ -][0-9])",
-                            extractfull.lower().replace('&#338;', '-'))
+    extractISBN = isbn_re.search(extractfull.lower().replace('&#338;', '-'))
     cleanISBN = False
     # Clean ISBN is the ISBN number without separators
     if extractISBN:
@@ -78,6 +80,15 @@ def isbn2Bib(isbn):
         return ''
 
 
+doi_re = re.compile('(?<=doi)/?:?\s?[0-9\.]{7}/\S*[0-9]')
+doi_pnas_re = re.compile('(?<=doi).?10.1073/pnas\.\d+')
+doi_jsb_re = re.compile('10\.1083/jcb\.\d{9}')
+clean_doi_re = re.compile('^/')
+clean_doi_fabse_re = re.compile('^10.1096')
+clean_doi_jcb_re = re.compile('^10.1083')
+clean_doi_len_re = re.compile(r'\d\.\d')
+
+
 def findDOI(src):
     """Search for a valid DOI in src.
 
@@ -99,29 +110,28 @@ def findDOI(src):
         tools.warning(extractfull[1])
         return False
     extractfull = extractfull[0]
-    extractDOI = re.search('(?<=doi)/?:?\s?[0-9\.]{7}/\S*[0-9]',
-                           extractfull.lower().replace('&#338;', '-'))
+    extractDOI = doi_re.search(extractfull.lower().replace('&#338;', '-'))
     if not extractDOI:
         # PNAS fix
-        extractDOI = re.search('(?<=doi).?10.1073/pnas\.\d+',
-                               extractfull.lower().replace('pnas', '/pnas'))
+        extractDOI = doi_pnas_re.search(extractfull.lower().replace('pnas',
+                                                                    '/pnas'))
         if not extractDOI:
             # JSB fix
-            extractDOI = re.search('10\.1083/jcb\.\d{9}', extractfull.lower())
+            extractDOI = doi_jsb_re.search(extractfull.lower())
 
     cleanDOI = False
     if extractDOI:
         cleanDOI = extractDOI.group(0).replace(':', '').replace(' ', '')
-        if re.search('^/', cleanDOI):
+        if clean_doi_re.search(cleanDOI):
             cleanDOI = cleanDOI[1:]
         # FABSE J fix
-        if re.search('^10.1096', cleanDOI):
+        if clean_doi_fabse_re.search(cleanDOI):
             cleanDOI = cleanDOI[:20]
         # Second JCB fix
-        if re.search('^10.1083', cleanDOI):
+        if clean_doi_jcb_re.search(cleanDOI):
             cleanDOI = cleanDOI[:21]
         if len(cleanDOI) > 40:
-            cleanDOItemp = re.sub(r'\d\.\d', '000', cleanDOI)
+            cleanDOItemp = clean_doi_len_re.sub('000', cleanDOI)
             reps = {'.': 'A', '-': '0'}
             cleanDOItemp = tools.replaceAll(cleanDOItemp[8:], reps)
             digitStart = 0