Updated reading and visual normalization tests for Perso-Arabic.

PiperOrigin-RevId: 672573963
google-research · Sep 9, 2024 · c18911c · c18911c
1 parent 9fce149
commit c18911c
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 26 deletions.
diff --git a/nisaba/scripts/abjad_alphabet/BUILD.bazel b/nisaba/scripts/abjad_alphabet/BUILD.bazel
@@ -154,23 +154,13 @@ nisaba_compile_script_lang_multi_grm_py(
 nisaba_grm_textproto_test(
     name = "visual_norm_test",
     grammar = ":visual_norm",
-    # TODO: Fix these tests and re-enable in TAP.
-    tags = [
-        "manual",
-        "notap",
-    ],
     textproto = "testdata/visual_norm.textproto",
     token_type = "byte",
 )
 
 nisaba_grm_textproto_test(
     name = "visual_norm_utf8_test",
     grammar = ":visual_norm_utf8",
-    # TODO: Fix these tests and re-enable in TAP.
-    tags = [
-        "manual",
-        "notap",
-    ],
     textproto = "testdata/visual_norm.textproto",
     token_type = "utf8",
 )
@@ -194,23 +184,13 @@ nisaba_compile_script_lang_multi_grm_py(
 nisaba_grm_textproto_test(
     name = "reading_norm_test",
     grammar = ":reading_norm",
-    # TODO: Fix these tests and re-enable in TAP.
-    tags = [
-        "manual",
-        "notap",
-    ],
     textproto = "testdata/reading_norm.textproto",
     token_type = "byte",
 )
 
 nisaba_grm_textproto_test(
     name = "reading_norm_utf8_test",
     grammar = ":reading_norm_utf8",
-    # TODO: Fix these tests and re-enable in TAP.
-    tags = [
-        "manual",
-        "notap",
-    ],
     textproto = "testdata/reading_norm.textproto",
     token_type = "utf8",
 )

diff --git a/nisaba/scripts/abjad_alphabet/testdata/reading_norm.textproto b/nisaba/scripts/abjad_alphabet/testdata/reading_norm.textproto
@@ -141,7 +141,7 @@ rewrite { rule: "CKB" input: "ڪەڵک" output: "کەڵک" }
 # ALEF
 rewrite { rule: "CKB" input: "خلجآن" output: "خلجان" }
 rewrite { rule: "CKB" input: "پکآپ" output: "پکاپ" }
-rewrite { rule: "CKB" input: "بةبآ" output: "بەبا" output: "بەبا" }
+rewrite { rule: "CKB" input: "بةبآ" output: "بەبا" }
 rewrite { rule: "CKB" input: "إِلَی" output: "اِلَی" }
 rewrite { rule: "CKB" input: "إیراد" output: "ایراد" }
 rewrite { rule: "CKB" input: "لنشأة" output: "لنشاە" }

diff --git a/nisaba/scripts/abjad_alphabet/testdata/visual_norm.textproto b/nisaba/scripts/abjad_alphabet/testdata/visual_norm.textproto
@@ -610,19 +610,19 @@ rewrite { rule: "PA" input: "تبں۬اؤں۬ا" output: "تبناؤنا" }
 rewrite { rule: "PA" input: "ادھنیٔم" output: "ادھنئم" }
 
 # KAF → KEHEH
-rewrite { rule: "PA" input: "كاں" output: "کاں" output: "کاں" }
+rewrite { rule: "PA" input: "كاں" output: "کاں" }
 
 # YEH → FARSI YEH
-rewrite { rule: "PA" input: "خريد" output: "خرید" output: "خرید" }
+rewrite { rule: "PA" input: "خريد" output: "خرید" }
 
 # RNOON → TTEH
-rewrite { rule: "PA" input: "ڻَنگیا" output: "ٹَنگیا" output: "ٹَنگیا" }
+rewrite { rule: "PA" input: "ڻَنگیا" output: "ٹَنگیا" }
 
 # TEH MARBUTA → TEH MARBUTA GOAL
-rewrite { rule: "PA" input: "ة" output: "ۃ" output: "ۃ" }
+rewrite { rule: "PA" input: "ة" output: "ۃ" }
 
 # HEH GOAL WITH HAMZA ABOVE → HEH, HAMZA ABOVE
-rewrite { rule: "PA" input: "ۂ" output: "هٔ" output: "هٔ" }
+rewrite { rule: "PA" input: "ۂ" output: "هٔ" }
 
 # Normalizations for isolated characters