From 620c721662c3ddd8d8ca8838861b9c4ba3ea66e7 Mon Sep 17 00:00:00 2001
From: Joe <jo3.l.dev@outlook.com>
Date: Thu, 4 Jan 2024 23:26:08 -0800
Subject: [PATCH] fix(english-preset): don't include skip-non-alphabetic
 transformer

For #23, #46.

BREAKING CHANGE: Using the default English preset, Obscenity will no longer strip non-alphabetic characters from the input text before matching.

This addresses a class of egregious false negatives in previous versions (see #23), but introduces a regression where cases such as 'f u c k' (with the space) will no longer be detected by default. We expect to provide a more comprehensive fix in the next minor release.

If desired, it remains possible to revert to the previous behavior by providing a custom set of transformers to the matcher.
---
 README.md                                    |  3 +--
 src/preset/english.ts                        |  4 ++--
 src/transformer/skip-non-alphabetic/index.ts | 10 +++++++++-
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index 7472154..f7f2c27 100644
--- a/README.md
+++ b/README.md
@@ -109,8 +109,7 @@ With the English preset, Obscenity (correctly) finds matches in all of the follo
 - **fk** you
 - **ffuk** you
 - i like **a$$es**
-- **ʃ𝐟ʃὗƈ ｋ** ỹоứ
-- **f .... !!! uuuuuuuuu ccc k**
+- <!-- prettier-ignore --> ʃ𝐟ʃὗƈｋ ỹоứ
 
 ...and it **does not match** on the following:
 
diff --git a/src/preset/english.ts b/src/preset/english.ts
index e80e060..8b6bfe7 100644
--- a/src/preset/english.ts
+++ b/src/preset/english.ts
@@ -4,7 +4,6 @@ import { pattern } from '../pattern/Pattern';
 import { collapseDuplicatesTransformer } from '../transformer/collapse-duplicates';
 import { resolveConfusablesTransformer } from '../transformer/resolve-confusables';
 import { resolveLeetSpeakTransformer } from '../transformer/resolve-leetspeak';
-import { skipNonAlphabeticTransformer } from '../transformer/skip-non-alphabetic';
 import { toAsciiLowerCaseTransformer } from '../transformer/to-ascii-lowercase';
 
 /**
@@ -15,7 +14,8 @@ export const englishRecommendedBlacklistMatcherTransformers = [
 	resolveConfusablesTransformer(),
 	resolveLeetSpeakTransformer(),
 	toAsciiLowerCaseTransformer(),
-	skipNonAlphabeticTransformer(),
+	// See #23 and #46.
+	// skipNonAlphabeticTransformer(),
 	collapseDuplicatesTransformer({
 		defaultThreshold: 1,
 		customThresholds: new Map([
diff --git a/src/transformer/skip-non-alphabetic/index.ts b/src/transformer/skip-non-alphabetic/index.ts
index e967588..054e00f 100644
--- a/src/transformer/skip-non-alphabetic/index.ts
+++ b/src/transformer/skip-non-alphabetic/index.ts
@@ -7,10 +7,18 @@ import { createSimpleTransformer } from '../Transformers';
  * comprised of alphabetic characters (the pattern `hello` does not match
  * `h.e.l.l.o` by default, but does with this transformer).
  *
+ * **Warning**
+ *
+ * This transformation is not part of the default set of transformations, as
+ * there are some known rough edges with false negatives; see
+ * [#23](https://github.com/jo3-l/obscenity/issues/23) and
+ * [#46](https://github.com/jo3-l/obscenity/issues/46) on the GitHub issue
+ * tracker.
+ *
  * **Application order**
  *
  * It is recommended that this transformer be applied near the end of the
- * transformer chain.
+ * transformer chain, if at all.
  *
  * @example
  * ```typescript