From 9ce235f39ee1209f372b03beb2c99ded053d406e Mon Sep 17 00:00:00 2001
From: Alex Bezzubov <bzz@apache.org>
Date: Fri, 3 Mar 2023 23:17:32 +0100
Subject: [PATCH] test: add new corner cases for linguist v7.23

test plan
 - go test -run '^Test_EnryOnLinguistCorpus$' github.com/go-enry/go-enry/v2
---
 README.md               |  4 ++++
 linguist_corpus_test.go | 10 ++++++++--
 utils_test.go           |  3 ++-
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index ff769e6..047232d 100644
--- a/README.md
+++ b/README.md
@@ -174,6 +174,10 @@ Parsing [linguist/samples](https://github.com/github/linguist/tree/master/sample
 
 - [Heuristics for ".csc", ".gsc" and ".gsh" extension](https://github.com/github/linguist/blob/7469c7982d93f2ad922230d712f586a353dc1a42/lib/linguist/heuristics.yml#L650-L651) in GSC could not be parsed, due to unsupported non-backtracking subexpressions in RE2 regexp engine.
 
+- [Heuristic for ".txt"](https://github.com/github/linguist/blob/bf853f1c663903e3ee35935189760191f1c45e1c/lib/linguist/heuristics.yml#L680-L702) detecting 'Adblock Filter List' regexp syntax not supported by RE2
+
+- [IsVendor('bootstrap.css') == false](https://github.com/github/linguist/blob/v7.23.0/lib/linguist/vendor.yml#L77) v7.23 first unsupported RE syntax outside content heuristics
+
 - As of [Linguist v5.3.2](https://github.com/github/linguist/releases/tag/v5.3.2) it is using [flex-based scanner in C for tokenization](https://github.com/github/linguist/pull/3846). Enry still uses [extract_token](https://github.com/github/linguist/pull/3846/files#diff-d5179df0b71620e3fac4535cd1368d15L60) regex-based algorithm. See [#193](https://github.com/src-d/enry/issues/193).
 
 - Bayesian classifier can't distinguish "SQL" from "PLpgSQL. See [#194](https://github.com/src-d/enry/issues/194).
diff --git a/linguist_corpus_test.go b/linguist_corpus_test.go
index a8856fd..98059ef 100644
--- a/linguist_corpus_test.go
+++ b/linguist_corpus_test.go
@@ -24,9 +24,15 @@ func Test_EnryOnLinguistCorpus(t *testing.T) {
 func (s *linguistCorpusSuite) TestLinguistSamples() {
 	const filenamesDir = "filenames"
 	var cornerCases = map[string]bool{
-		"drop_stuff.sql":        true, // https://github.com/src-d/enry/issues/194
-		"textobj-rubyblock.vba": true, // Because of unsupported negative lookahead RE syntax (https://github.com/github/linguist/blob/8083cb5a89cee2d99f5a988f165994d0243f0d1e/lib/linguist/heuristics.yml#L521)
+		"drop_stuff.sql":        false, // not the case in v7.23, https://github.com/src-d/enry/issues/194
+		"textobj-rubyblock.vba": true,  // unsupported negative lookahead RE syntax (https://github.com/github/linguist/blob/8083cb5a89cee2d99f5a988f165994d0243f0d1e/lib/linguist/heuristics.yml#L521)
 		// .es and .ice fail heuristics parsing, but do not fail any tests
+		// 'Adblock Filter List' hack https://github.com/github/linguist/blob/bf853f1c663903e3ee35935189760191f1c45e1c/lib/linguist/heuristics.yml#L680-L702
+		"Imperial Units Remover.txt": true,
+		"abp-filters-anti-cv.txt":    true,
+		"anti-facebook.txt":          true,
+		"fake-news.txt":              true,
+		"test_rules.txt":             true,
 	}
 
 	var total, failed, ok, other int
diff --git a/utils_test.go b/utils_test.go
index 75f2a22..4d426c1 100644
--- a/utils_test.go
+++ b/utils_test.go
@@ -51,8 +51,9 @@ var vendorTests = []struct {
 	{false, "some/python/venv/", false},
 	{false, "foo/.imageset/bar", true},
 	{false, "Vagrantfile", true},
+	{false, "custom.bootstrap.css", true},
 	{true, "src/bootstrap-custom.js", true},
-	// {true, "/css/bootstrap.rtl.css", true}, // from linguist v7.23
+	{true, "/css/bootstrap.rtl.css", true}, // from linguist v7.23
 }
 
 func TestIsVendor(t *testing.T) {