From c7aa10384a2548167466b4c61f9eff29ed8611f6 Mon Sep 17 00:00:00 2001
From: nsfisis <nsfisis@gmail.com>
Date: Mon, 17 Aug 2026 07:13:02 +0900
Subject: refactor(preg): report unmatched groups as null throughout

The shim carried two reporting modes for the preg_* $matches maps: PHP's
default (trailing unmatched groups dropped, interior ones ""), and the
PREG_UNMATCHED_AS_NULL form, picked by calling a *_unmatched_as_null()
variant. The regex crate hands out Option<Match>, which maps onto the
null form directly, and no caller distinguished a dropped group from a
null one -- preg_match() and preg_match_all2() already reported nulls
unconditionally. Keep only the null form; the shim API no longer mirrors
PHP's flag set, which is intended.

Preg::is_match_with_indexed_captures() modelled PHP's "unset" as a
truncated Vec<String>, and now returns Vec<Option<String>>. That is what
Composer actually does: Preg::isMatch() always sets
PREG_UNMATCHED_AS_NULL, and its callers test groups with `!== null`.

preg_match_all(), preg_match_all_set_order() and
preg_split_delim_capture() still hand back Vec<String> and keep the ""
form.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
---
 crates/shirabe/src/command/fund_command.rs            |  2 +-
 crates/shirabe/src/command/update_command.rs          |  6 ++----
 crates/shirabe/src/installer/binary_installer.rs      |  6 +++---
 crates/shirabe/src/package/version/version_guesser.rs |  6 +++---
 crates/shirabe/src/repository/vcs/svn_driver.rs       | 12 ++++++------
 crates/shirabe/src/util/hg.rs                         |  2 +-
 crates/shirabe/src/util/platform.rs                   |  4 +---
 7 files changed, 17 insertions(+), 21 deletions(-)

(limited to 'crates/shirabe/src')

diff --git a/crates/shirabe/src/command/fund_command.rs b/crates/shirabe/src/command/fund_command.rs
index 7f2dd24c..109943d6 100644
--- a/crates/shirabe/src/command/fund_command.rs
+++ b/crates/shirabe/src/command/fund_command.rs
@@ -67,7 +67,7 @@ impl FundCommand {
                     php_regex!(r"{^https://github.com/([^/]+)$}"),
                     &url,
                 )
-                && let Some(sponsor) = matches.into_iter().nth(1)
+                && let Some(sponsor) = matches.into_iter().nth(1).flatten()
             {
                 url = format!("https://github.com/sponsors/{}", sponsor);
             }
diff --git a/crates/shirabe/src/command/update_command.rs b/crates/shirabe/src/command/update_command.rs
index 38a79e30..2eca6db7 100644
--- a/crates/shirabe/src/command/update_command.rs
+++ b/crates/shirabe/src/command/update_command.rs
@@ -466,10 +466,8 @@ impl Command for UpdateCommand {
                 let Some(matches) = matches else {
                     continue;
                 };
-                let constraint = parser.parse_constraints(&format!(
-                    "~{}",
-                    matches.get(1).cloned().unwrap_or_default()
-                ))?;
+                let constraint = parser
+                    .parse_constraints(&format!("~{}", matches[1].clone().unwrap_or_default()))?;
                 if let Some(existing) = temporary_constraints.get(&package.get_name()) {
                     temporary_constraints.insert(
                         package.get_name(),
diff --git a/crates/shirabe/src/installer/binary_installer.rs b/crates/shirabe/src/installer/binary_installer.rs
index d5ece82f..606e943f 100644
--- a/crates/shirabe/src/installer/binary_installer.rs
+++ b/crates/shirabe/src/installer/binary_installer.rs
@@ -328,10 +328,10 @@ impl BinaryInstaller {
             &bin_contents,
         ) {
             // carry over the existing shebang if present, otherwise add our own
-            let proxy_code = if m.get(1).is_none() {
+            let proxy_code = if m[1].is_none() {
                 "#!/usr/bin/env php".to_string()
             } else {
-                trim(m.get(1).map(|s| s.as_str()).unwrap_or(""), None)
+                trim(m[1].as_deref().unwrap_or(""), None)
             };
             let bin_path_exported = self
                 .filesystem
@@ -377,7 +377,7 @@ impl BinaryInstaller {
                 $data = str_replace('__FILE__', var_export($this->realpath, true), $data);"
                     .to_string();
             }
-            if trim(m.first().map(|s| s.as_str()).unwrap_or(""), None) != "<?php" {
+            if trim(m[0].as_deref().unwrap_or(""), None) != "<?php" {
                 stream_hint =
                     " using a stream wrapper to prevent the shebang from being output on PHP<8\n *"
                         .to_string();
diff --git a/crates/shirabe/src/package/version/version_guesser.rs b/crates/shirabe/src/package/version/version_guesser.rs
index 4f46919e..4b5187f2 100644
--- a/crates/shirabe/src/package/version/version_guesser.rs
+++ b/crates/shirabe/src/package/version/version_guesser.rs
@@ -704,9 +704,9 @@ impl VersionGuesser {
             );
 
             if let Some(matches) = Preg::is_match_with_indexed_captures(&url_pattern, &output) {
-                let m1 = matches.get(1).cloned().unwrap_or_default();
-                let m2 = matches.get(2).cloned();
-                let m3 = matches.get(3).cloned();
+                let m1 = matches[1].clone().unwrap_or_default();
+                let m2 = matches[2].clone();
+                let m3 = matches[3].clone();
                 if let Some(m2) = m2.as_ref()
                     && let Some(m3) = m3.as_ref()
                     && (branches_path == *m2 || tags_path == *m2)
diff --git a/crates/shirabe/src/repository/vcs/svn_driver.rs b/crates/shirabe/src/repository/vcs/svn_driver.rs
index 297e8f33..db8c43f0 100644
--- a/crates/shirabe/src/repository/vcs/svn_driver.rs
+++ b/crates/shirabe/src/repository/vcs/svn_driver.rs
@@ -260,10 +260,10 @@ impl SvnDriver {
         let (path, rev) = if let Some(m) =
             Preg::is_match_with_indexed_captures(php_regex!(r"{^(.+?)(@\d+)?/$}"), &identifier)
         {
-            if m.get(2).is_some() {
+            if m[2].is_some() {
                 (
-                    m.get(1).cloned().unwrap_or_default(),
-                    m.get(2).cloned().unwrap_or_default(),
+                    m[1].clone().unwrap_or_default(),
+                    m[2].clone().unwrap_or_default(),
                 )
             } else {
                 (identifier.clone(), String::new())
@@ -300,10 +300,10 @@ impl SvnDriver {
         let (path, rev) = if let Some(m) =
             Preg::is_match_with_indexed_captures(php_regex!(r"{^(.+?)(@\d+)?/$}"), &identifier)
         {
-            if m.get(2).is_some() {
+            if m[2].is_some() {
                 (
-                    m.get(1).cloned().unwrap_or_default(),
-                    m.get(2).cloned().unwrap_or_default(),
+                    m[1].clone().unwrap_or_default(),
+                    m[2].clone().unwrap_or_default(),
                 )
             } else {
                 (identifier.clone(), String::new())
diff --git a/crates/shirabe/src/util/hg.rs b/crates/shirabe/src/util/hg.rs
index 8570af6d..d9e58623 100644
--- a/crates/shirabe/src/util/hg.rs
+++ b/crates/shirabe/src/util/hg.rs
@@ -158,7 +158,7 @@ impl Hg {
                         &output,
                     )
                 {
-                    return matches.into_iter().nth(1);
+                    return matches.into_iter().nth(1).flatten();
                 }
                 None
             })
diff --git a/crates/shirabe/src/util/platform.rs b/crates/shirabe/src/util/platform.rs
index 21ad869c..629854b6 100644
--- a/crates/shirabe/src/util/platform.rs
+++ b/crates/shirabe/src/util/platform.rs
@@ -95,14 +95,12 @@ impl Platform {
         // Regex pattern compatibility:
         // The original pattern uses a conditional subpattern to make the trailing `%` required
         // only for the `%VAR%` form. The Rust regex crate does not support conditionals, so the
-        // two forms are written as an explicit alternation: `$VAR` or `%VAR%`. The branch that did
-        // not participate is reported as an empty string, which `\w+` can never capture.
+        // two forms are written as an explicit alternation: `$VAR` or `%VAR%`.
         Preg::replace_callback(
             php_regex!(r"#^(?:\$(?P<dvar>\w+)|%(?P<pvar>\w+)%)(?P<path>.*)#"),
             |matches: &PregMatchedGroups| -> String {
                 let var = matches
                     .get(&CaptureKey::ByName("dvar".to_string()))
-                    .filter(|dvar| !dvar.is_empty())
                     .or_else(|| matches.get(&CaptureKey::ByName("pvar".to_string())))
                     .map(|s| s.as_str())
                     .unwrap_or("");
-- 
cgit v1.3.1-4-g156e