support --ignore-regex with --diff, #862, #865, #868

AlDanial · Dec 14, 2024 · 804cd9e · 804cd9e
1 parent 0774046
commit 804cd9e
Show file tree

Hide file tree

Showing 7 changed files with 206 additions and 39 deletions.
diff --git a/Unix/cloc b/Unix/cloc
@@ -3040,6 +3040,12 @@ sub count_filesets {                         # {{{1
                 foreach (@comm_L) { $_ = lc }
                 foreach (@comm_R) { $_ = lc }
             }
+            my $n_code_removed_L = 0;
+            my $n_code_removed_R = 0;
+            @code_L = apply_ignores(\@code_L, $Lang_L, $file_L, $rha_ignore_regex,
+                                    \$n_code_removed_L);
+            @code_R = apply_ignores(\@code_R, $Lang_R, $file_R, $rha_ignore_regex,
+                                    \$n_code_removed_R);
             # step 3: compute code diffs
             array_diff("$file_L v. $file_R"   ,   # in
                        \@code_L               ,   # in
@@ -3154,8 +3160,40 @@ sub count_filesets {                         # {{{1
         "n_filepairs_compared" => $n_file_pairs_compared
     }
 } # 1}}}
+sub apply_ignores {                          # {{{1
+    my ($ra_lines             , # in
+        $language             , # in
+        $file                 , # in
+        $rha_ignore_regex     , # in
+        $rs_lines_code_removed, # out
+       ) = @_;
+    my @output = ();
+    print "-> apply_ignores($file, $language)\n" if $opt_v > 2;
+
+    if (%{$rha_ignore_regex} and defined($rha_ignore_regex->{$language})) {
+        foreach my $line (@{$ra_lines}) {
+            my $keep = 1;
+            foreach my $regex (@{$rha_ignore_regex->{$language}}) {
+                if ($line =~ m{$regex}) {
+                    print "apply_ignores reject '$line' in $file because of '$regex'\n"
+                        if $opt_v > 4;
+                    $keep = 0;
+                    ++${$rs_lines_code_removed};
+                    last;
+                }
+            }
+            push @output, $line if $keep;
+        }
+    } else {
+        @output = @{$ra_lines};
+    }
+
+    print "<- apply_ignores(${$rs_lines_code_removed})\n" if $opt_v > 2;
+    return @output;
+} # 1}}}
 sub write_alignment_data {                   # {{{1
     my ($filename, $n_filepairs_compared, $data ) = @_;
+    print "-> write_alignment_data($filename)\n" if $opt_v > 2;
     my @output = ();
     if ( $data->{'added'} ) {
         my %added_lines = %{$data->{'added'}};
@@ -3181,9 +3219,12 @@ sub write_alignment_data {                   # {{{1
         }
     }
     write_file($filename, {}, @output);
+    print "<- write_alignment_data\n" if $opt_v > 2;
 } # 1}}}
 sub exclude_dir_validates {                  # {{{1
     my ($rh_Exclude_Dir) = @_;
+    # $opt_v hasn't been set yet
+    # print "-> exclude_dir_validates\n" if $opt_v > 2;
     my $is_OK = 1;
     foreach my $dir (keys %{$rh_Exclude_Dir}) {
         if (($ON_WINDOWS and $dir =~ m{\\}) or ($dir =~ m{/})) {
@@ -3194,6 +3235,7 @@ sub exclude_dir_validates {                  # {{{1
     if (!$is_OK) {
         warn "Use '--fullpath --not-match-d=REGEX' instead\n";
     }
+    # print "<- exclude_dir_validates\n" if $opt_v > 2;
     return $is_OK;
 } # 1}}}
 sub process_exclude_list_file {              # {{{1
@@ -6966,23 +7008,12 @@ sub call_counter {                           # {{{1
     @lines = rm_comments(\@lines, $language, $file,
                                \%EOL_Continuation_re, $ra_Errors);
 
-    if (%{$rha_ignore_regex} and defined($rha_ignore_regex->{$language})) {
-        my @keep_lines = ();
-        foreach my $line (@lines) {
-            my $keep = 1;
-            foreach my $regex (@{$rha_ignore_regex->{$language}}) {
-                if ($line =~ m{$regex}) {
-print "reject '$line' in $file because of '$regex'\n" if $opt_v > 4;
-                    $keep = 0;
-                    last;
-                }
-            }
-            push @keep_lines, $line if $keep;
-        }
-        @lines = @keep_lines;
-    }
+    my $n_code_removed = 0;
+    @lines = apply_ignores(\@lines, $language, $file, $rha_ignore_regex,
+                           \$n_code_removed);
+    $total_lines -= $n_code_removed;
 
-    my $comment_lines = $total_lines - $blank_lines - scalar  @lines;
+    my $comment_lines = $total_lines - $blank_lines - scalar @lines;
     if ($opt_strip_comments) {
         my $stripped_file = "";
         if ($opt_original_dir) {

diff --git a/Unix/t/01_opts.t b/Unix/t/01_opts.t
@@ -872,6 +872,13 @@ my @Tests = (
                    'ref'  => '../tests/outputs/issues/862/results.yaml',
                 },
 
+                {
+                   'name' => '--ignore-regex --diff (github issues #862, #865, #868)',
+                   'cd'   => '../tests/inputs/issues/862',
+                   'args' => '--ignore-regex="*|import" --diff a.py b.py',
+                   'ref'  => '../tests/outputs/issues/862/diff_results.yaml',
+                },
+
             );
 
 # Special cases:

diff --git a/cloc b/cloc
@@ -3030,6 +3030,12 @@ sub count_filesets {                         # {{{1
                 foreach (@comm_L) { $_ = lc }
                 foreach (@comm_R) { $_ = lc }
             }
+            my $n_code_removed_L = 0;
+            my $n_code_removed_R = 0;
+            @code_L = apply_ignores(\@code_L, $Lang_L, $file_L, $rha_ignore_regex,
+                                    \$n_code_removed_L);
+            @code_R = apply_ignores(\@code_R, $Lang_R, $file_R, $rha_ignore_regex,
+                                    \$n_code_removed_R);
             # step 3: compute code diffs
             array_diff("$file_L v. $file_R"   ,   # in
                        \@code_L               ,   # in
@@ -3144,8 +3150,40 @@ sub count_filesets {                         # {{{1
         "n_filepairs_compared" => $n_file_pairs_compared
     }
 } # 1}}}
+sub apply_ignores {                          # {{{1
+    my ($ra_lines             , # in
+        $language             , # in
+        $file                 , # in
+        $rha_ignore_regex     , # in
+        $rs_lines_code_removed, # out
+       ) = @_;
+    my @output = ();
+    print "-> apply_ignores($file, $language)\n" if $opt_v > 2;
+
+    if (%{$rha_ignore_regex} and defined($rha_ignore_regex->{$language})) {
+        foreach my $line (@{$ra_lines}) {
+            my $keep = 1;
+            foreach my $regex (@{$rha_ignore_regex->{$language}}) {
+                if ($line =~ m{$regex}) {
+                    print "apply_ignores reject '$line' in $file because of '$regex'\n"
+                        if $opt_v > 4;
+                    $keep = 0;
+                    ++${$rs_lines_code_removed};
+                    last;
+                }
+            }
+            push @output, $line if $keep;
+        }
+    } else {
+        @output = @{$ra_lines};
+    }
+
+    print "<- apply_ignores(${$rs_lines_code_removed})\n" if $opt_v > 2;
+    return @output;
+} # 1}}}
 sub write_alignment_data {                   # {{{1
     my ($filename, $n_filepairs_compared, $data ) = @_;
+    print "-> write_alignment_data($filename)\n" if $opt_v > 2;
     my @output = ();
     if ( $data->{'added'} ) {
         my %added_lines = %{$data->{'added'}};
@@ -3171,9 +3209,12 @@ sub write_alignment_data {                   # {{{1
         }
     }
     write_file($filename, {}, @output);
+    print "<- write_alignment_data\n" if $opt_v > 2;
 } # 1}}}
 sub exclude_dir_validates {                  # {{{1
     my ($rh_Exclude_Dir) = @_;
+    # $opt_v hasn't been set yet
+    # print "-> exclude_dir_validates\n" if $opt_v > 2;
     my $is_OK = 1;
     foreach my $dir (keys %{$rh_Exclude_Dir}) {
         if (($ON_WINDOWS and $dir =~ m{\\}) or ($dir =~ m{/})) {
@@ -3184,6 +3225,7 @@ sub exclude_dir_validates {                  # {{{1
     if (!$is_OK) {
         warn "Use '--fullpath --not-match-d=REGEX' instead\n";
     }
+    # print "<- exclude_dir_validates\n" if $opt_v > 2;
     return $is_OK;
 } # 1}}}
 sub process_exclude_list_file {              # {{{1
@@ -6956,23 +6998,12 @@ sub call_counter {                           # {{{1
     @lines = rm_comments(\@lines, $language, $file,
                                \%EOL_Continuation_re, $ra_Errors);
 
-    if (%{$rha_ignore_regex} and defined($rha_ignore_regex->{$language})) {
-        my @keep_lines = ();
-        foreach my $line (@lines) {
-            my $keep = 1;
-            foreach my $regex (@{$rha_ignore_regex->{$language}}) {
-                if ($line =~ m{$regex}) {
-print "reject '$line' in $file because of '$regex'\n" if $opt_v > 4;
-                    $keep = 0;
-                    last;
-                }
-            }
-            push @keep_lines, $line if $keep;
-        }
-        @lines = @keep_lines;
-    }
+    my $n_code_removed = 0;
+    @lines = apply_ignores(\@lines, $language, $file, $rha_ignore_regex,
+                           \$n_code_removed);
+    $total_lines -= $n_code_removed;
 
-    my $comment_lines = $total_lines - $blank_lines - scalar  @lines;
+    my $comment_lines = $total_lines - $blank_lines - scalar @lines;
     if ($opt_strip_comments) {
         my $stripped_file = "";
         if ($opt_original_dir) {

diff --git a/tests/inputs/issues/862/a.py b/tests/inputs/issues/862/a.py
@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+import numpy as np
+
+from pylab import gca
+
+labels = ["Baseline", "System"]
+data =   [3.75               , 4.75]
+error =  [0.3497             , 0.3108]
+
+xlocations = na.array(range(len(data)))+0.5
+width = 0.6
+# bar chart with hollow bars:
+bar(xlocations, data, yerr=error, width=width, edgecolor='k', facecolor='none')
+yticks(range(0, 8))
+xticks(xlocations+ width/2, labels)
+xlim(0, xlocations[-1]+width*2)
+title("Average Ratings on the Training Set")
+gca().get_xaxis().tick_bottom()
+gca().get_yaxis().tick_left()
+
+show()
diff --git a/tests/inputs/issues/862/b.py b/tests/inputs/issues/862/b.py
@@ -0,0 +1,21 @@
+#!/usr/bin/env python
+import numpy.numarray as na
+
+from pylab import *
+
+labels = ["Baseline", "System"]
+data =   [3.75               , 4.75]
+error =  [0.3497             , 0.3108]
+
+xlocations = na.array(range(len(data)))+0.5
+width = 0.5
+# bar chart with hollow bars:
+bar(xlocations, data, yerr=error, width=width, edgecolor='k', facecolor='none')
+yticks(range(0, 8))
+xticks(xlocations+ width/2, labels)
+xlim(0, xlocations[-1]+width*2)
+title("Average Ratings on the Training Set")
+gca().get_xaxis().tick_bottom()
+gca().get_yaxis().tick_left()
+
+show()
diff --git a/tests/outputs/issues/862/diff_results.yaml b/tests/outputs/issues/862/diff_results.yaml
@@ -0,0 +1,56 @@
+---
+# github.com/AlDanial/cloc
+header : 
+  cloc_url           : github.com/AlDanial/cloc
+  cloc_version       : 2.03
+  elapsed_seconds    : 0.00476408004760742
+  n_files            : 1
+  n_lines            : 15
+  files_per_second   : 209.904113702332
+  lines_per_second   : 3148.56170553498
+  report_file        : ../../../outputs/issues/862/diff_results.yaml
+added :
+  'Python' :
+    comment : 0
+    code : 0
+    blank : 0
+    nFiles : 0
+same :
+  'Python' :
+    comment : 1
+    code : 13
+    blank : 0
+    nFiles : 0
+modified :
+  'Python' :
+    comment : 0
+    code : 1
+    blank : 0
+    nFiles : 1
+removed :
+  'Python' :
+    comment : 0
+    code : 0
+    blank : 0
+    nFiles : 0
+SUM :
+  added :
+    nFiles : 0
+    comment : 0
+    code : 0
+    blank : 0
+  same :
+    nFiles : 0
+    comment : 1
+    code : 13
+    blank : 0
+  modified :
+    nFiles : 1
+    comment : 0
+    code : 1
+    blank : 0
+  removed :
+    nFiles : 0
+    comment : 0
+    code : 0
+    blank : 0
diff --git a/tests/outputs/issues/862/results.yaml b/tests/outputs/issues/862/results.yaml
@@ -3,24 +3,24 @@
 header : 
   cloc_url           : github.com/AlDanial/cloc
   cloc_version       : 2.03
-  elapsed_seconds    : 0.0048370361328125
+  elapsed_seconds    : 0.00425577163696289
   n_files            : 2
-  n_lines            : 16
-  files_per_second   : 413.476340694006
-  lines_per_second   : 3307.81072555205
+  n_lines            : 11
+  files_per_second   : 469.950028011204
+  lines_per_second   : 2584.72515406162
   report_file        : results.yaml
 'C' :
   nFiles: 1
   blank: 1
-  comment: 4
+  comment: 0
   code: 5
 'Fortran 77' :
   nFiles: 1
   blank: 1
-  comment: 3
+  comment: 2
   code: 2
 SUM: 
   blank: 2
-  comment: 7
+  comment: 2
   code: 7
   nFiles: 2