lint fixes

5 files changed, 10 insertions, 18 deletions

diff --git a/mapreduce/.pylintrc b/mapreduce/.pylintrc
index 2ec9967..5dc3ce0 100644
--- a/mapreduce/.pylintrc
+++ b/mapreduce/.pylintrc
@@ -1,5 +1,5 @@
 [MESSAGES CONTROL]
-disable=C0323,W0142,C0301,C0103,C0111,E0213,C0302,C0203,W0703,R0201,W0223
+disable=C0323,W0142,C0301,C0103,C0111,E0213,C0302,C0203,W0703,R0201,W0223,bad-continuation,arguments-differ,unidiomatic-typecheck
 
 [REPORTS]
 output-format=colorized
diff --git a/mapreduce/backfill_hbase_from_cdx.py b/mapreduce/backfill_hbase_from_cdx.py
index 2643195..72331b0 100755
--- a/mapreduce/backfill_hbase_from_cdx.py
+++ b/mapreduce/backfill_hbase_from_cdx.py
@@ -16,7 +16,6 @@ TODO:
 - sentry integration for error reporting
 """
 
-import sys
 import json
 import happybase
 import mrjob
@@ -56,8 +55,8 @@ class MRCDXBackfillHBase(MRJob):
             host = self.options.hbase_host
             # TODO: make these configs accessible from... mrconf.cfg?
             hb_conn = happybase.Connection(host=host, transport="framed",
-                protocol="compact")
-        except Exception as err:
+                                           protocol="compact")
+        except Exception:
             raise Exception("Couldn't connect to HBase using host: {}".format(host))
         self.hb_table = hb_conn.table(self.options.hbase_table)
 
@@ -67,9 +66,6 @@ class MRCDXBackfillHBase(MRJob):
 
         if (raw_cdx.startswith(' ') or raw_cdx.startswith('filedesc') or
                 raw_cdx.startswith('#')):
-
-            # Skip line
-            # XXX: tests don't cover this path; need coverage!
             self.increment_counter('lines', 'invalid')
             yield _, dict(status="invalid", reason="line prefix")
             return
@@ -87,8 +83,8 @@ class MRCDXBackfillHBase(MRJob):
 
         key = info.pop('key')
         info['f:c'] = json.dumps(info['f:c'], sort_keys=True, indent=None)
-        info['file:cdx'] = json.dumps(info['file:cdx'], sort_keys=True,
-            indent=None)
+        info['file:cdx'] = json.dumps(info['file:cdx'],
+                                      sort_keys=True, indent=None)
 
         self.hb_table.put(key, info)
         self.increment_counter('lines', 'success')
@@ -97,4 +93,3 @@ class MRCDXBackfillHBase(MRJob):
 
 if __name__ == '__main__': # pragma: no cover
     MRCDXBackfillHBase.run()
-
diff --git a/mapreduce/common.py b/mapreduce/common.py
index 1b8e572..6710044 100644
--- a/mapreduce/common.py
+++ b/mapreduce/common.py
@@ -14,7 +14,7 @@ def normalize_mime(raw):
         if raw.startswith(norm):
             return norm
 
-    # Special cases 
+    # Special cases
     if raw.startswith('application/xml'):
         return 'text/xml'
     if raw.startswith('application/x-pdf'):
@@ -23,14 +23,14 @@ def normalize_mime(raw):
 
 
 def test_normalize_mime():
-    assert normalize_mime("asdf") == None
+    assert normalize_mime("asdf") is None
     assert normalize_mime("application/pdf") == "application/pdf"
     assert normalize_mime("application/pdf+journal") == "application/pdf"
     assert normalize_mime("Application/PDF") == "application/pdf"
-    assert normalize_mime("application/p") == None
+    assert normalize_mime("application/p") is None
     assert normalize_mime("application/xml+stuff") == "text/xml"
     assert normalize_mime("application/x-pdf") == "application/pdf"
-    assert normalize_mime("application/x-html") == None
+    assert normalize_mime("application/x-html") is None
 
 
 def parse_cdx_line(raw_cdx):
@@ -65,7 +65,7 @@ def parse_cdx_line(raw_cdx):
     warc_file = warc.split('/')[-1]
     try:
         dt_iso = datetime.strptime(dt, "%Y%m%d%H%M%S").isoformat()
-    except:
+    except Exception:
         return None
 
     # 'i' intentionally not set
diff --git a/mapreduce/grobid2json.py b/mapreduce/grobid2json.py
index 52a3125..c1ff1f1 100755
--- a/mapreduce/grobid2json.py
+++ b/mapreduce/grobid2json.py
@@ -23,9 +23,7 @@ A flag can be specified to disable copyright encumbered bits (--no-emcumbered):
 Prints JSON to stdout, errors to stderr
 """
 
-import os
 import io
-import sys
 import json
 import argparse
 import xml.etree.ElementTree as ET
diff --git a/mapreduce/xml2json.py b/mapreduce/xml2json.py
index f956014..df5064f 100644
--- a/mapreduce/xml2json.py
+++ b/mapreduce/xml2json.py
@@ -1,6 +1,5 @@
 
 import json
-import sys
 import xmltodict
 
 with open('tests/files/23b29ea36382680716be08fc71aa81bd226e8a85.xml', 'rb') as f: