citekey generation and support

.gitignore

@@ -1,2 +1,3 @@
 build/
 *.pyc
+tests/.papers

.pit/pit-52bc4daefb7ab51f

@@ -0,0 +1,15 @@
+[header]
+title = search inside pdfs over a playlist
+id = 52bc4daefb7ab51f88974325dd202aaa37f9c60d
+status = open
+type = feature
+author = Fabien Benureau
+mail = fabien.benureau+git@gmail.com
+date = 2012-10-07 at 20:10 UCT
+
+[eventlog]
+opened[0] = opened the 2012-10-07 at 20:10 UCT by Fabien Benureau
+
+[discussion]
+desc = # enter your description here
+

papers/commands/add_cmd.py

@@ -15,7 +15,6 @@ def parser(subparsers, config):
     parser.add_argument('bibfile', help='bibtex, bibtexml or bibyaml file')
     return parser
 
-
 def command(config, pdffile, bibfile):
     """
     :param pdffilepath  path (no url yet) to a pdf or ps file
@@ -49,10 +48,13 @@ def command(config, pdffile, bibfile):
         print(pretty.bib_desc(bib_data))
         files.write_bibdata(bib_data, filename)
 
-    papers = files.read_papers()
+    papers = files.load_papers()
     count = papers.get('header', 'count')
     papers.set('header', 'count', int(count) + 1)
-    papers.set('papers', 'p' + count, filename)
+    
+    citekey = pretty.create_citekey(bib_data)
+    papers.set('papers', citekey, filename)
+    papers.set('citekeys', 'ck' + count, citekey)
 
     files.write_papers(papers)
     files.write_meta(meta, filename)

papers/commands/init_cmd.py

@@ -30,6 +30,7 @@ def command(config):
         papers.add_section('header')
         papers.set('header', 'count', 0)
         papers.add_section('papers')
+        papers.add_section('citekeys')
         files.write_papers(papers)
 
     else:

papers/commands/list_cmd.py

@@ -1,5 +1,6 @@
 from .. import files
 from .. import pretty
+from .. import color
 
 import subprocess
 import tempfile
@@ -9,15 +10,16 @@ def parser(subparsers, config):
     return parser
 
 def command(config):
-    papers = files.read_papers()
+    papers = files.load_papers()
 
     articles = []
-    for p in papers.options('papers'):
-        filename = papers.get('papers', p)
-        number = p[1:]
+    for p in papers.options('citekeys'):
+        number = p[2:]
+        citekey = papers.get('citekeys', p)
+        filename = papers.get('papers', citekey)
         bibdata = files.load_bibdata(filename + '.bibyaml')
         bibdesc = pretty.bib_oneliner(bibdata)
-        articles.append('{:3d}   {}'.format(int(number), bibdesc))
+        articles.append('{:3d} {}{}{}{}   {}'.format(int(number), color.purple, citekey, color.end, (8-len(citekey))*' ', bibdesc))
 
     with tempfile.NamedTemporaryFile(suffix=".tmp", delete=True) as tmpf:
         tmpf.write('\n'.join(articles))

papers/commands/open_cmd.py

@@ -13,11 +13,15 @@ def parser(subparsers, config):
     return parser
 
 def command(config, citekey):
-    papers = files.read_papers()
+    papers = files.load_papers()
     try:
-        filename = papers.get('papers', 'p' + str(citekey))
+        filename = papers.get('papers', str(citekey))
     except configparser.NoOptionError:
-        print('{}error{}: paper with citekey {}{}{} not found{}'.format(
+        try:
+            ck = papers.get('citekeys', 'ck'+str(citekey))
+            filename = papers.get('papers', str(ck))
+        except configparser.NoOptionError:
+            print('{}error{}: paper with citekey or number {}{}{} not found{}'.format(
                 color.red, color.grey, color.cyan, citekey, color.grey, color.end))
             exit(-1)
     meta_data = files.load_meta(filename)

papers/files.py

@@ -106,7 +106,7 @@ def load_externalbibfile(fullbibpath):
 def write_papers(config):
     write_configfile(config, find_papersdir() + os.sep + 'papers')
 
-def read_papers():
+def load_papers():
     return read_configfile(find_papersdir() + os.sep + 'papers')
 
 def load_bibdata(filename):

papers/pretty.py

@@ -26,3 +26,33 @@ def bib_desc(bib_data):
     s += '\n'
     s += '\n'.join('{}: {}'.format(k, v) for k, v in article.fields.items())
     return s
+
+alphabet = 'abcdefghijklmopqrstuvwxyz'
+
+try:
+    import ConfigParser as configparser
+except ImportError:
+    import configparser
+import files
+
+def create_citekey(bib_data):
+    """Create a cite key unique to the paper"""
+    article = bib_data.entries[list(bib_data.entries.keys())[0]]
+    first_author = article.persons['author'][0]
+    year = article.fields['year']
+    prefix = '{}{}'.format(first_author.last()[0][:6], year[2:])
+
+    papers = files.load_papers()
+    letter = 0, False
+    citekey = None
+    
+    citekey = prefix
+    while not letter[1]:
+        try:
+            papers.get('papers', citekey)
+            citekey = prefix + alphabet[letter[0]]
+            letter = letter[0]+1, False
+        except configparser.NoOptionError:
+            letter = letter[0], True
+
+    return citekey

tests/data/pagerank.bib

@@ -7,7 +7,7 @@
             type = {Technical Report},
        publisher = {Stanford InfoLab},
             year = {1999},
-     institution = {Stanford InfoLab},
+         journal = {Stanford InfoLab},
              url = {http://ilpubs.stanford.edu:8090/422/},
         abstract = {The importance of a Web page is an inherently subjective matter, which depends on the readers interests, knowledge and attitudes. But there is still much that can be said objectively about the relative importance of Web pages. This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them. We compare PageRank to an idealized random Web surfer. We show how to efficiently compute PageRank for large numbers of pages. And, we show how to apply PageRank to search and to user navigation.}
 }

tests/data/pagerank.bib.bak

@@ -0,0 +1,14 @@
+@techreport{ilprints422,
+          number = {1999-66},
+           month = {November},
+          author = {Lawrence Page and Sergey Brin and Rajeev Motwani and Terry Winograd},
+            note = {Previous number = SIDL-WP-1999-0120},
+           title = {The PageRank Citation Ranking: Bringing Order to the Web.},
+            type = {Technical Report},
+       publisher = {Stanford InfoLab},
+            year = {1999},
+     institution = {Stanford InfoLab},
+             url = {http://ilpubs.stanford.edu:8090/422/},
+        abstract = {The importance of a Web page is an inherently subjective matter, which depends on the readers interests, knowledge and attitudes. But there is still much that can be said objectively about the relative importance of Web pages. This paper describes PageRank, a mathod for rating Web pages objectively and mechanically, effectively measuring the human interest and attention devoted to them. We compare PageRank to an idealized random Web surfer. We show how to efficiently compute PageRank for large numbers of pages. And, we show how to apply PageRank to search and to user navigation.}
+}
+

tests/test.sh

@@ -1,7 +1,8 @@
 #!/usr/bin/env bash
+rm -Rf .papers;
 papers init;
 papers list;
 papers add data/pagerank.pdf data/pagerank.bib;
 papers list;
 papers open 0;
-rm -Rf .papers;
+papers open Page99;