Repository navigation
Add packagename.Normalize as the PEP 503 entry point #68
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
Merged
Merged
Changes from all commits
Commits
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
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 |
|---|---|---|
| @@ -1,45 +1,21 @@ | ||
| // SPDX-License-Identifier: Apache-2.0 OR MIT | ||
| // | ||
| // Portions of this file are ported from pypa/packaging | ||
| // (https://github.com/pypa/packaging), specifically packaging/utils.py's | ||
| // canonicalize_name, used under the Apache License, Version 2.0 | ||
| // (dual-licensed Apache-2.0 OR BSD-2-Clause; see NOTICE for full license and | ||
| // copyright detail). | ||
| // Changed: translated from a single re.sub regex into an explicit | ||
| // rune-by-rune loop, since extra-name normalization sits on a | ||
| // per-dependency hot path; behavior (lowercase, collapse -/_/. runs to one | ||
| // "-") is unchanged. | ||
|
|
||
| package extras | ||
|
|
||
| import "strings" | ||
| import "github.com/posit-dev/go-python-packaging/internal/canonname" | ||
|
|
||
| // Normalize canonicalizes a Python extra name per PEP 685: lowercase the | ||
| // name, then collapse any run of "-", "_", or "." into a single "-". | ||
| // | ||
| // This mirrors pypa/packaging's canonicalize_name (PEP 503/685) without | ||
| // using a regular expression, since extra-name normalization sits on a | ||
| // per-dependency, per-extra hot path during dependency resolution. | ||
| // Lowercasing follows Python's str.lower() across all of Unicode, so the | ||
| // result matches pypa/packaging for non-ASCII input too (up to differences | ||
| // between Go's and Python's Unicode versions). Bytes that are not valid UTF-8 | ||
| // pass through unchanged. | ||
| // | ||
| // PEP 685 adopts the PEP 503 project-name rule unchanged, so this returns | ||
| // exactly what packagename.Normalize returns; both delegate to one shared | ||
| // implementation. It mirrors pypa/packaging's canonicalize_name and uses no | ||
| // regular expression. | ||
| func Normalize(name string) string { | ||
| var b strings.Builder | ||
| b.Grow(len(name)) | ||
|
|
||
| inSep := false | ||
| for _, r := range name { | ||
| switch r { | ||
| case '-', '_', '.': | ||
| if !inSep { | ||
| b.WriteByte('-') | ||
| inSep = true | ||
| } | ||
| default: | ||
| inSep = false | ||
| if r >= 'A' && r <= 'Z' { | ||
| r += 'a' - 'A' | ||
| } | ||
| b.WriteRune(r) | ||
| } | ||
| } | ||
|
|
||
| return b.String() | ||
| return canonname.Normalize(name) | ||
| } |
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 +1,193 @@ | ||
| // SPDX-License-Identifier: Apache-2.0 OR MIT | ||
| // | ||
| // Portions of this file are ported from pypa/packaging | ||
| // (https://github.com/pypa/packaging), specifically packaging/utils.py's | ||
| // canonicalize_name, used under the Apache License, Version 2.0 | ||
| // (dual-licensed Apache-2.0 OR BSD-2-Clause; see NOTICE for full license and | ||
| // copyright detail). The Final_Sigma rule in finalSigma follows CPython's | ||
| // handle_capital_sigma in Objects/unicodeobject.c (Unicode Standard §3.13). | ||
| // Changed: upstream's str.lower(), str.replace, and repeated "--" collapse | ||
| // (which emulate PEP 503's re.sub(r"[-_.]+", "-", name).lower()) are | ||
| // translated into a single loop with an ASCII fast path and a non-allocating | ||
| // early return for already-normalized names, since name normalization sits on | ||
| // a per-dependency hot path; behavior (lowercase, collapse -/_/. runs to one | ||
| // "-") is unchanged. str.lower() is reproduced with Go's unicode tables, so | ||
| // results for characters whose case data differs between Go's and the running | ||
| // Python's Unicode version can differ. The validate=True option is not ported. | ||
|
|
||
| // Package canonname holds the single implementation of Python name | ||
| // canonicalization shared by PEP 503 project names (package packagename) and | ||
| // PEP 685 extra names (package extras). The two PEPs specify the same | ||
| // transformation; keeping one implementation means the public entry points | ||
| // cannot drift apart. | ||
| package canonname | ||
|
|
||
| import ( | ||
| "strings" | ||
| "unicode" | ||
| "unicode/utf8" | ||
| ) | ||
|
|
||
| const ( | ||
| capitalDottedI = 'İ' // U+0130; the only unconditional multi-rune lowercase mapping | ||
| capitalSigma = 'Σ' // U+03A3; lowercases to ς or σ depending on context | ||
| smallSigma = 'σ' // U+03C3 | ||
| finalSmallSig = 'ς' // U+03C2 | ||
| ) | ||
|
|
||
| // Normalize returns the canonical form of a Python name per PEP 503 (and | ||
| // PEP 685, which adopts the same rule): the name is lowercased the way | ||
| // Python's str.lower() does it, and any run of "-", "_", or "." collapses to | ||
| // a single "-". | ||
| // | ||
| // Lowercasing covers all of Unicode, not just ASCII, including str.lower()'s | ||
| // two special cases: "İ" (U+0130) becomes "i" plus U+0307, and "Σ" becomes | ||
| // final "ς" at the end of a word and "σ" elsewhere. Bytes that are not valid | ||
| // UTF-8 pass through unchanged. | ||
| // | ||
| // This mirrors pypa/packaging's canonicalize_name without using a regular | ||
| // expression, since it sits on a per-dependency, per-extra hot path during | ||
| // dependency resolution. An already-normalized name is returned as-is, | ||
| // without allocating. | ||
| func Normalize(name string) string { | ||
| // Fast path: most names are already normalized; avoid allocating. | ||
| if isNormalized(name) { | ||
| return name | ||
| } | ||
|
|
||
| // strings.Builder, not a []byte plus string(b): String() does not copy, | ||
| // so the slow path allocates once. | ||
| var b strings.Builder | ||
| b.Grow(len(name) + 1) | ||
| inSep := false | ||
| for i := 0; i < len(name); { | ||
| c := name[i] | ||
| if c < utf8.RuneSelf { | ||
| switch c { | ||
| case '-', '_', '.': | ||
| if !inSep { | ||
| b.WriteByte('-') | ||
| inSep = true | ||
| } | ||
| default: | ||
| inSep = false | ||
| if 'A' <= c && c <= 'Z' { | ||
| c += 'a' - 'A' | ||
| } | ||
| b.WriteByte(c) | ||
| } | ||
| i++ | ||
| continue | ||
| } | ||
|
|
||
| // No non-ASCII rune lowercases to a separator, so this always ends a | ||
| // separator run. | ||
| inSep = false | ||
| r, size := utf8.DecodeRuneInString(name[i:]) | ||
| switch { | ||
| case r == utf8.RuneError && size == 1: | ||
| b.WriteByte(c) // invalid UTF-8: copy the byte unchanged | ||
| case r == capitalDottedI: | ||
| b.WriteString("i̇") | ||
| case r == capitalSigma: | ||
| if finalSigma(name, i, i+size) { | ||
| b.WriteRune(finalSmallSig) | ||
| } else { | ||
| b.WriteRune(smallSigma) | ||
| } | ||
| default: | ||
| b.WriteRune(unicode.ToLower(r)) | ||
| } | ||
| i += size | ||
| } | ||
| return b.String() | ||
| } | ||
|
|
||
| // isNormalized reports whether Normalize(name) == name: name has no "_" or | ||
| // ".", no run of two or more "-", and no rune that lowercasing would change. | ||
| func isNormalized(name string) bool { | ||
| prevSep := false | ||
| for i := 0; i < len(name); { | ||
| c := name[i] | ||
| if c < utf8.RuneSelf { | ||
| switch { | ||
| case c == '_' || c == '.', 'A' <= c && c <= 'Z': | ||
| return false | ||
| case c == '-': | ||
| if prevSep { | ||
| return false | ||
| } | ||
| prevSep = true | ||
| default: | ||
| prevSep = false | ||
| } | ||
| i++ | ||
| continue | ||
| } | ||
|
|
||
| prevSep = false | ||
| r, size := utf8.DecodeRuneInString(name[i:]) | ||
| valid := r != utf8.RuneError || size != 1 | ||
| if valid && (r == capitalDottedI || unicode.ToLower(r) != r) { | ||
| return false | ||
| } | ||
| i += size | ||
| } | ||
| return true | ||
| } | ||
|
|
||
| // finalSigma reports whether the capital sigma at name[start:end] is in the | ||
| // Final_Sigma context: preceded by a cased letter (skipping case-ignorable | ||
| // runes) and not followed by one (again skipping case-ignorable runes). | ||
| // | ||
| // The context is evaluated on the original name, before separators are | ||
| // replaced, because str.lower() runs first upstream. Invalid UTF-8 bytes, | ||
| // which Python strings cannot hold, count as neither cased nor | ||
| // case-ignorable. | ||
| func finalSigma(name string, start, end int) bool { | ||
| before := false | ||
| for j := start; j > 0; { | ||
| r, size := utf8.DecodeLastRuneInString(name[:j]) | ||
| if size == 1 && r == utf8.RuneError { | ||
| break | ||
| } | ||
| if !isCaseIgnorable(r) { | ||
| before = isCased(r) | ||
| break | ||
| } | ||
| j -= size | ||
| } | ||
| if !before { | ||
| return false | ||
| } | ||
| for j := end; j < len(name); { | ||
| r, size := utf8.DecodeRuneInString(name[j:]) | ||
| if size == 1 && r == utf8.RuneError { | ||
| return true | ||
| } | ||
| if !isCaseIgnorable(r) { | ||
| return !isCased(r) | ||
| } | ||
| j += size | ||
| } | ||
| return true | ||
| } | ||
|
|
||
| // isCased reports the Unicode Cased property: Lowercase, Uppercase, or Lt. | ||
| func isCased(r rune) bool { | ||
| return unicode.IsLower(r) || unicode.IsUpper(r) || unicode.IsTitle(r) || | ||
| unicode.Is(unicode.Other_Lowercase, r) || unicode.Is(unicode.Other_Uppercase, r) | ||
| } | ||
|
|
||
| // isCaseIgnorable reports the Unicode Case_Ignorable property: general | ||
| // category Mn, Me, Cf, Lm, or Sk, or Word_Break MidLetter, MidNumLet, or | ||
| // Single_Quote. Go has no Word_Break tables, so those runes are listed. | ||
| func isCaseIgnorable(r rune) bool { | ||
| switch r { | ||
| case '\'', // Single_Quote | ||
| '.', '‘', '’', '․', '﹒', '＇', '．', // MidNumLet | ||
| ':', '·', '·', '՟', '״', '‧', '︓', '﹕', '：': // MidLetter | ||
| return true | ||
| } | ||
| return unicode.In(r, unicode.Mn, unicode.Me, unicode.Cf, unicode.Lm, unicode.Sk) | ||
| } |
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.