Merge pull request #160 from pubs/feat/stats

Adds the statistics command. (Fixes #8)

pubs/commands/__init__.py

@@ -6,9 +6,11 @@ from . import add_cmd
 from . import rename_cmd
 from . import remove_cmd
 from . import list_cmd
+from . import edit_cmd
+from . import tag_cmd
+from . import statistics_cmd
 # doc
 from . import doc_cmd
-from . import tag_cmd
 from . import note_cmd
 # bulk
 from . import export_cmd
@@ -16,5 +18,3 @@ from . import import_cmd
 # bonus
 from . import websearch_cmd
 from . import url_cmd
-
-from . import edit_cmd

pubs/commands/statistics_cmd.py

@@ -0,0 +1,33 @@
+from ..repo import Repository
+from ..uis import get_ui
+from .. import color
+
+
+def parser(subparsers, conf):
+    parser = subparsers.add_parser(
+        'statistics',
+        help="show statistics on the repository.")
+    return parser
+
+
+def command(conf, args):
+    ui = get_ui()
+    rp = Repository(conf)
+    papers = list(rp.all_papers())
+
+    paper_count = len(papers)
+    doc_count = sum([0 if p.docpath is None else 1 for p in papers])
+    tag_count = len(list(rp.get_tags()))
+    papers_with_tags = sum([0 if p.tags else 1 for p in papers])
+
+    ui.message(color.dye_out('Repository statistics:', 'bold'))
+    ui.message('Total papers: {}, {} ({}) have a document attached'.format(
+        color.dye_out('{:d}'.format(paper_count), 'bgreen'),
+        color.dye_out('{:d}'.format(doc_count), 'bold'),
+        '{:.0f}%'.format(100. * doc_count / paper_count),
+    ))
+    ui.message('Total tags: {}, {} ({}) of papers have at least one tag'.format(
+        color.dye_out('{:d}'.format(tag_count), 'bgreen'),
+        color.dye_out('{:d}'.format(papers_with_tags), 'bold'),
+        '{:.0f}%'.format(100. * papers_with_tags / paper_count),
+    ))

pubs/pubs_cmd.py

@@ -20,9 +20,11 @@ CORE_CMDS = collections.OrderedDict([
     ('rename', commands.rename_cmd),
     ('remove', commands.remove_cmd),
     ('list', commands.list_cmd),
+    ('edit', commands.edit_cmd),
+    ('tag', commands.tag_cmd),
+    ('statistics', commands.statistics_cmd),
 
     ('doc', commands.doc_cmd),
-    ('tag', commands.tag_cmd),
     ('note', commands.note_cmd),
 
     ('export', commands.export_cmd),
@@ -30,7 +32,6 @@ CORE_CMDS = collections.OrderedDict([
 
     ('websearch', commands.websearch_cmd),
     ('url', commands.url_cmd),
-    ('edit', commands.edit_cmd),
 ])
 
 

tests/test_usecase.py

@@ -925,6 +925,21 @@ class TestUsecase(DataCommandTestCase):
         self.assertFalse(os.path.isfile(self.default_conf_path))
         self.assertTrue(os.path.isfile(alt_conf))
 
+    def test_statistics(self):
+        cmds = ['pubs init',
+                'pubs add data/pagerank.bib',
+                'pubs add -d data/turing-mind-1950.pdf data/turing1950.bib',
+                'pubs add data/martius.bib',
+                'pubs add data/10.1371%2Fjournal.pone.0038236.bib',
+                'pubs tag Page99 A+B',
+                'pubs tag turing1950computing C',
+                'pubs statistics',
+                ]
+        out = self.execute_cmds(cmds)
+        lines = out[-1].splitlines()
+        self.assertEqual(lines[0], 'Repository statistics:')
+        self.assertEqual(lines[1], 'Total papers: 4, 1 (25%) have a document attached')
+        self.assertEqual(lines[2], 'Total tags: 3, 2 (50%) of papers have at least one tag')
 
 
 @ddt.ddt