-
-
Notifications
You must be signed in to change notification settings - Fork 2
test(tools): add unit tests for internal/ucd #162
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
AhmadAL-Quraan
wants to merge
3
commits into
dexpace:main
Choose a base branch
from
AhmadAL-Quraan:test/ucd-unit-tests
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,104 @@ | ||
| // Copyright (c) 2026 dexpace and Omar Aljarrah | ||
| // SPDX-License-Identifier: MIT | ||
|
|
||
| package ucd | ||
|
|
||
| import "testing" | ||
|
|
||
| func TestLoadBidiUnicodeDataBasic(t *testing.T) { | ||
| data := []byte( | ||
| "0041;LATIN CAPITAL LETTER A;Lu;0;L;;;;;N;;;;;\n" + | ||
| "0627;ARABIC LETTER ALEF;Lo;0;AL;;;;;N;;;;;\n", | ||
| ) | ||
| got, err := loadBidiUnicodeData(data) | ||
| if err != nil { | ||
| t.Fatalf("loadBidiUnicodeData: unexpected error: %v", err) | ||
| } | ||
| if len(got) != 2 { | ||
| t.Fatalf("loadBidiUnicodeData: got %d ranges, want 2", len(got)) | ||
| } | ||
| if got[0].start != 0x41 || got[0].jtype != "L" { | ||
| t.Errorf("got[0] = %+v, want start=0x41 class=L", got[0]) | ||
| } | ||
| if got[1].start != 0x627 || got[1].jtype != "AL" { | ||
| t.Errorf("got[1] = %+v, want start=0x627 class=AL", got[1]) | ||
| } | ||
| } | ||
|
|
||
| func TestLoadBidiUnicodeDataFiltersUntrackedClasses(t *testing.T) { | ||
| // B is Paragraph_Separator, which is not in bidiClasses; such code points | ||
| // must be dropped entirely from the result, not recorded with an empty class. | ||
| data := []byte("2029;PARAGRAPH SEPARATOR;Zp;0;B;;;;;N;;;;;\n") | ||
| got, err := loadBidiUnicodeData(data) | ||
| if err != nil { | ||
| t.Fatalf("loadBidiUnicodeData: unexpected error: %v", err) | ||
| } | ||
| if len(got) != 0 { | ||
| t.Fatalf("loadBidiUnicodeData = %+v, want empty (Paragraph_Separator is untracked)", got) | ||
| } | ||
| } | ||
|
|
||
| func TestLoadBidiUnicodeDataFirstLastBlock(t *testing.T) { | ||
| // The expanded range takes the Bidi_Class of the Last (closing) row, mirroring | ||
| // the Mark/Virama pass's First/Last handling. | ||
| data := []byte( | ||
| "3400;<CJK Ideograph Extension A, First>;Lo;0;L;;;;;N;;;;;\n" + | ||
| "4DBF;<CJK Ideograph Extension A, Last>;Lo;0;L;;;;;N;;;;;\n", | ||
| ) | ||
| got, err := loadBidiUnicodeData(data) | ||
| if err != nil { | ||
| t.Fatalf("loadBidiUnicodeData: unexpected error: %v", err) | ||
| } | ||
| if len(got) != 1 || got[0].start != 0x3400 || got[0].end != 0x4DBF || got[0].jtype != "L" { | ||
| t.Fatalf("got = %+v, want a single range [0x3400, 0x4DBF] class L", got) | ||
| } | ||
| } | ||
|
|
||
| func TestLoadBidiUnicodeDataSkipsShortLines(t *testing.T) { | ||
| data := []byte("\n0041;A;Lu;0;L;;;;;N;;;;;\n") | ||
| got, err := loadBidiUnicodeData(data) | ||
| if err != nil { | ||
| t.Fatalf("loadBidiUnicodeData: unexpected error: %v", err) | ||
| } | ||
| if len(got) != 1 { | ||
| t.Fatalf("loadBidiUnicodeData: got %d ranges, want 1 (blank line skipped)", len(got)) | ||
| } | ||
| } | ||
|
|
||
| func TestLoadBidiUnicodeDataInvalidCodePoint(t *testing.T) { | ||
| data := []byte("ZZZZ;BOGUS;Lu;0;L;;;;;N;;;;;\n") | ||
| if _, err := loadBidiUnicodeData(data); err == nil { | ||
| t.Fatal("loadBidiUnicodeData with invalid code point: expected error, got nil") | ||
| } | ||
| } | ||
|
|
||
| func TestLoadBidiUnicodeDataSortsByStart(t *testing.T) { | ||
| // Out-of-order input must come back sorted by start, mirroring the sort step | ||
| // in loadBidiUnicodeData. | ||
| data := []byte( | ||
| "0627;ARABIC LETTER ALEF;Lo;0;AL;;;;;N;;;;;\n" + | ||
| "0041;LATIN CAPITAL LETTER A;Lu;0;L;;;;;N;;;;;\n", | ||
| ) | ||
| got, err := loadBidiUnicodeData(data) | ||
| if err != nil { | ||
| t.Fatalf("loadBidiUnicodeData: unexpected error: %v", err) | ||
| } | ||
| if len(got) != 2 || got[0].start != 0x41 || got[1].start != 0x627 { | ||
| t.Fatalf("loadBidiUnicodeData did not sort by start: got %+v", got) | ||
| } | ||
| } | ||
|
|
||
| func TestBidiClassesTrackedSet(t *testing.T) { | ||
| // Pin the exact set of classes the RFC 5893 rule consults, so an accidental | ||
| // addition or removal in bidi.go is caught here rather than only surfacing as | ||
| // a silent behavior change in the generated table. | ||
| want := []string{"L", "R", "AL", "EN", "ES", "ET", "AN", "CS", "NSM", "BN", "ON"} | ||
| if len(bidiClasses) != len(want) { | ||
| t.Fatalf("bidiClasses has %d entries, want %d: %v", len(bidiClasses), len(want), bidiClasses) | ||
| } | ||
| for _, class := range want { | ||
| if !bidiClasses[class] { | ||
| t.Errorf("bidiClasses[%q] = false, want true", class) | ||
| } | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is the version the other two loaders' tests should look like: it asserts
len(got) == 1, so it pins both that the blank line was skipped and that the real record survived. The NFC equivalent only asserts emptiness, and the validity equivalent doesn't exist — see the comments on those files.