From 06d2c5c884eee0b5b663730f4d379a7ceae3a8e4 Mon Sep 17 00:00:00 2001 From: nsfisis Date: Sat, 1 Aug 2026 05:26:16 +0900 Subject: feat(php-shim): implement Phar/PharData and the zlib/bzip2 functions Adopt the tar, flate2, and bzip2 crates to fill in the phar.rs and compress.rs todos: PharData tar/zip reading, building, and whole-archive compression, plus a native .phar reader that follows the php.net file-format manual and verifies hash-based signatures. Callers now propagate the constructor/extract errors PHP throws, and fwrite accepts byte strings so gzread no longer needs lossy UTF-8. The native .phar writing API stays todo!() (no call sites; Composer's Compiler is not ported) and OPENSSL phar signatures are accepted unverified (TODO(phase-c)). This unblocks Tar::getComposerJson and the tar/phar/gzip downloaders; tar_test (7), artifact_repository_test (2), and phar_archiver_test zip (1) are un-ignored. The archive command itself still panics because ArchiveManager::archive always generates glob excludes whose look-ahead regexes the regex crate cannot compile; converting those patterns to regex-compatible ones is a separate, still-undecided work item. Co-Authored-By: Claude Fable 5 --- crates/shirabe/src/util/tar.rs | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'crates/shirabe/src/util/tar.rs') diff --git a/crates/shirabe/src/util/tar.rs b/crates/shirabe/src/util/tar.rs index 55b6a960..792d1c4f 100644 --- a/crates/shirabe/src/util/tar.rs +++ b/crates/shirabe/src/util/tar.rs @@ -7,7 +7,7 @@ pub struct Tar; impl Tar { pub fn get_composer_json(path_to_archive: &str) -> anyhow::Result> { - let phar = PharData::new(path_to_archive.to_string()); + let phar = PharData::new(path_to_archive.to_string())?; if !phar.valid() { return Ok(None); @@ -16,9 +16,20 @@ impl Tar { Ok(Some(Self::extract_composer_json_from_folder(&phar)?)) } + /// The content bytes are decoded strictly: a composer.json that is not valid + /// UTF-8 could never survive the JSON parsing that follows in PHP either. + fn content_to_string(content: Vec) -> anyhow::Result { + String::from_utf8(content).map_err(|_| { + anyhow::anyhow!(RuntimeException { + message: "composer.json in the archive is not valid UTF-8".to_string(), + code: 0, + }) + }) + } + fn extract_composer_json_from_folder(phar: &PharData) -> anyhow::Result { if let Some(file) = phar.get("composer.json") { - return Ok(file.get_content()); + return Self::content_to_string(file.get_content()); } let mut top_level_paths: IndexMap = IndexMap::new(); @@ -49,7 +60,7 @@ impl Tar { if !top_level_paths.is_empty() && let Some(file) = phar.get(&composer_json_path) { - return Ok(file.get_content()); + return Self::content_to_string(file.get_content()); } Err(anyhow::anyhow!(RuntimeException { -- cgit v1.3.1