From b1ef3dc8fee44a703e6fbaf736331ba31e7b3857 Mon Sep 17 00:00:00 2001
From: Virgil Dupras <hsoft@hardcoded.net>
Date: Wed, 8 Jun 2016 12:24:35 -0400
Subject: [PATCH] Simplify progress report during scanning

We now get less progress feedback, but in exchange, our progress job is
simpler. Previously, our progress bar would often get wonky towards the
end of the scan and I didn't have the energy to debug that.

Besides, people don't care about that level of progress feedback.
---
 core/engine.py            |  4 ++--
 core/scanner.py           | 12 ++++--------
 core/tests/engine_test.py | 14 --------------
 3 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/core/engine.py b/core/engine.py
index f4be53bc..33a5f4b3 100644
--- a/core/engine.py
+++ b/core/engine.py
@@ -449,7 +449,7 @@ class Group:
             return self[0]
 
 
-def get_groups(matches, j=job.nulljob):
+def get_groups(matches):
     """Returns a list of :class:`Group` from ``matches``.
 
     Create groups out of match pairs in the smartest way possible.
@@ -458,7 +458,7 @@ def get_groups(matches, j=job.nulljob):
     dupe2group = {}
     groups = []
     try:
-        for match in j.iter_with_progress(matches, tr("Grouped %d/%d matches"), JOB_REFRESH_RATE):
+        for match in matches:
             first, second, _ = match
             first_group = dupe2group.get(first)
             second_group = dupe2group.get(second)
diff --git a/core/scanner.py b/core/scanner.py
index a2640b3f..5919b664 100644
--- a/core/scanner.py
+++ b/core/scanner.py
@@ -130,14 +130,13 @@ class Scanner:
         raise NotImplementedError()
 
     def get_dupe_groups(self, files, ignore_list=None, j=job.nulljob):
-        j = j.start_subjob([8, 2])
         for f in (f for f in files if not hasattr(f, 'is_ref')):
             f.is_ref = False
         files = remove_dupe_paths(files)
         logging.info("Getting matches. Scan type: %d", self.scan_type)
         matches = self._getmatches(files, j)
         logging.info('Found %d matches' % len(matches))
-        j.set_progress(100, tr("Removing false matches"))
+        j.set_progress(100, tr("Almost done! Fiddling with results..."))
         # In removing what we call here "false matches", we first want to remove, if we scan by
         # folders, we want to remove folder matches for which the parent is also in a match (they're
         # "duplicated duplicates if you will). Then, we also don't want mixed file kinds if the
@@ -160,16 +159,14 @@ class Scanner:
         matches = [m for m in matches if m.first.path.exists() and m.second.path.exists()]
         matches = [m for m in matches if not (m.first.is_ref and m.second.is_ref)]
         if ignore_list:
-            j = j.start_subjob(2)
-            iter_matches = j.iter_with_progress(matches, tr("Processed %d/%d matches against the ignore list"))
             matches = [
-                m for m in iter_matches
+                m for m in matches
                 if not ignore_list.AreIgnored(str(m.first.path), str(m.second.path))
             ]
         logging.info('Grouping matches')
-        groups = engine.get_groups(matches, j)
-        matched_files = dedupe([m.first for m in matches] + [m.second for m in matches])
+        groups = engine.get_groups(matches)
         if self.scan_type in {ScanType.Filename, ScanType.Fields, ScanType.FieldsNoOrder, ScanType.Tag}:
+            matched_files = dedupe([m.first for m in matches] + [m.second for m in matches])
             self.discarded_file_count = len(matched_files) - sum(len(g) for g in groups)
         else:
             # Ticket #195
@@ -185,7 +182,6 @@ class Scanner:
             self.discarded_file_count = 0
         groups = [g for g in groups if any(not f.is_ref for f in g)]
         logging.info('Created %d groups' % len(groups))
-        j.set_progress(100, tr("Doing group prioritization"))
         for g in groups:
             g.prioritize(self._key_func, self._tie_breaker)
         return groups
diff --git a/core/tests/engine_test.py b/core/tests/engine_test.py
index d905ee18..c84a6f49 100644
--- a/core/tests/engine_test.py
+++ b/core/tests/engine_test.py
@@ -803,20 +803,6 @@ class TestCaseget_groups:
         r = get_groups([m1, m2, m3])
         eq_(3, len(r[0]))
 
-    def test_job(self):
-        def do_progress(p, d=''):
-            self.log.append(p)
-            return True
-
-        self.log = []
-        j = job.Job(1, do_progress)
-        m1, m2, m3 = get_match_triangle()
-        #101%: To make sure it is processed first so the job test works correctly
-        m4 = Match(NamedObject('a', True), NamedObject('a', True), 101)
-        get_groups([m1, m2, m3, m4], j)
-        eq_(0, self.log[0])
-        eq_(100, self.log[-1])
-
     def test_group_admissible_discarded_dupes(self):
         # If, with a (A, B, C, D) set, all match with A, but C and D don't match with B and that the
         # (A, B) match is the highest (thus resulting in an (A, B) group), still match C and D