diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index bb3d87d..c405f5d 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -17,7 +17,7 @@ jobs: runs-on: ${{ matrix.os }} steps: - - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: persist-credentials: false @@ -35,7 +35,7 @@ jobs: lint: runs-on: ubuntu-latest steps: - - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: persist-credentials: false diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml index c08cfa6..9c99e5d 100644 --- a/.github/workflows/publish.yml +++ b/.github/workflows/publish.yml @@ -20,12 +20,12 @@ jobs: contents: read steps: - name: Check out the repo - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 + uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 with: persist-credentials: false - name: Log in to the Container registry - uses: docker/login-action@06fb636fac595d6fb4b28a5dfcb21a6f5091859c + uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0 with: registry: ghcr.io username: ${{ github.actor }} diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 5d32181..f06cecd 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -14,7 +14,7 @@ jobs: runs-on: ubuntu-latest steps: - - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: fetch-depth: 0 persist-credentials: false diff --git a/.github/workflows/swagger.yml b/.github/workflows/swagger.yml index 625f944..e99aecf 100644 --- a/.github/workflows/swagger.yml +++ b/.github/workflows/swagger.yml @@ -12,7 +12,7 @@ jobs: swagger: runs-on: ubuntu-latest steps: - - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: persist-credentials: false diff --git a/.github/workflows/zizmor.yml b/.github/workflows/zizmor.yml index 4df0e18..df06c5f 100644 --- a/.github/workflows/zizmor.yml +++ b/.github/workflows/zizmor.yml @@ -21,9 +21,9 @@ jobs: security-events: write steps: - name: Checkout - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 with: persist-credentials: false - name: Run zizmor - uses: zizmorcore/zizmor-action@6fc4b006235f201fdab3722e17240ab420d580e5 # v0.6.1 + uses: zizmorcore/zizmor-action@6599ee8b7a49aef6a770f63d261d214911a7ce02 # v0.6.0 diff --git a/go.mod b/go.mod index e6e0a08..c460ec7 100644 --- a/go.mod +++ b/go.mod @@ -5,10 +5,9 @@ go 1.25.6 require ( github.com/BurntSushi/toml v1.6.0 github.com/CycloneDX/cyclonedx-go v0.11.0 - github.com/git-pkgs/archives v0.4.0 + github.com/git-pkgs/archives v0.3.1 github.com/git-pkgs/cooldown v0.1.1 github.com/git-pkgs/enrichment v0.6.4 - github.com/git-pkgs/magic v0.1.0 github.com/git-pkgs/purl v0.1.15 github.com/git-pkgs/registries v0.6.4 github.com/git-pkgs/spdx v0.1.4 @@ -17,7 +16,7 @@ require ( github.com/go-chi/chi/v5 v5.3.1 github.com/jmoiron/sqlx v1.4.0 github.com/lib/pq v1.12.3 - github.com/prometheus/client_golang v1.24.0 + github.com/prometheus/client_golang v1.23.2 github.com/prometheus/client_model v0.6.2 github.com/spdx/tools-golang v0.5.7 github.com/swaggo/swag v1.16.6 @@ -25,7 +24,7 @@ require ( golang.org/x/sync v0.22.0 google.golang.org/protobuf v1.36.11 gopkg.in/yaml.v3 v3.0.1 - modernc.org/sqlite v1.55.0 + modernc.org/sqlite v1.54.0 ) require ( @@ -226,8 +225,8 @@ require ( github.com/pelletier/go-toml/v2 v2.2.4 // indirect github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect github.com/pmezard/go-difflib v1.0.0 // indirect - github.com/prometheus/common v0.70.0 // indirect - github.com/prometheus/procfs v0.21.1 // indirect + github.com/prometheus/common v0.67.5 // indirect + github.com/prometheus/procfs v0.20.1 // indirect github.com/quasilyte/go-ruleguard v0.4.5 // indirect github.com/quasilyte/go-ruleguard/dsl v0.3.23 // indirect github.com/quasilyte/gogrep v0.5.0 // indirect @@ -291,7 +290,7 @@ require ( go.opentelemetry.io/otel/trace v1.44.0 // indirect go.uber.org/multierr v1.11.0 // indirect go.uber.org/zap v1.27.1 // indirect - go.yaml.in/yaml/v2 v2.4.4 // indirect + go.yaml.in/yaml/v2 v2.4.3 // indirect go.yaml.in/yaml/v3 v3.0.4 // indirect golang.org/x/crypto v0.53.0 // indirect golang.org/x/exp v0.0.0-20260218203240-3dfff04db8fa // indirect @@ -299,7 +298,7 @@ require ( golang.org/x/mod v0.37.0 // indirect golang.org/x/net v0.56.0 // indirect golang.org/x/oauth2 v0.36.0 // indirect - golang.org/x/sys v0.47.0 // indirect + golang.org/x/sys v0.46.0 // indirect golang.org/x/text v0.38.0 // indirect golang.org/x/tools v0.47.0 // indirect golang.org/x/xerrors v0.0.0-20240903120638-7835f813f4da // indirect diff --git a/go.sum b/go.sum index c239240..5621b47 100644 --- a/go.sum +++ b/go.sum @@ -244,14 +244,12 @@ github.com/fzipp/gocyclo v0.6.0 h1:lsblElZG7d3ALtGMx9fmxeTKZaLLpU8mET09yN4BBLo= github.com/fzipp/gocyclo v0.6.0/go.mod h1:rXPyn8fnlpa0R2csP/31uerbiVBugk5whMdlyaLkLoA= github.com/ghostiam/protogetter v0.3.20 h1:oW7OPFit2FxZOpmMRPP9FffU4uUpfeE/rEdE1f+MzD0= github.com/ghostiam/protogetter v0.3.20/go.mod h1:FjIu5Yfs6FT391m+Fjp3fbAYJ6rkL/J6ySpZBfnODuI= -github.com/git-pkgs/archives v0.4.0 h1:KNmmIsLiSH27lUdT27EfUkQXFaLgXV5KezE81iyOIgo= -github.com/git-pkgs/archives v0.4.0/go.mod h1:tfio0OIuPKEBKHs/UCL5XBUvYmKpnvtnba2iDlfSd6g= +github.com/git-pkgs/archives v0.3.1 h1:GKUuw++0YXAAElxweVHiR4AaSShKKYoVQmyxlF5blG4= +github.com/git-pkgs/archives v0.3.1/go.mod h1:408oQv3FxLCtePa33zp3sg3njXnwH74vnHZFxkRqoPo= github.com/git-pkgs/cooldown v0.1.1 h1:9OqqzCB8gANz/y44SmqGD0Jp8Qtu81D1sCbKl6Ehg7w= github.com/git-pkgs/cooldown v0.1.1/go.mod h1:v7APuK/UouTiu8mWQZbdDmj7DfxxkGUeuhjaRB5gv9E= github.com/git-pkgs/enrichment v0.6.4 h1:mGrfenttwmcUfPXRkWpB0wBJiiGj55ltniUh66Pq4bU= github.com/git-pkgs/enrichment v0.6.4/go.mod h1:zz1vPUak/w8Jhajll0KDRN2MjKaEYeCzQTxumWnVhqY= -github.com/git-pkgs/magic v0.1.0 h1:xLrqq7CMXB9g5bJnmJyKw17Rvlh0GFiEmO6e5RFsoeY= -github.com/git-pkgs/magic v0.1.0/go.mod h1:3ndidt+yvFaI1M0aEkkzkOlFnLPkeVQASIUojazcxCI= github.com/git-pkgs/packageurl-go v0.3.1 h1:WM3RBABQZLaRBxgKyYughc3cVBE8KyQxbSC6Jt5ak7M= github.com/git-pkgs/packageurl-go v0.3.1/go.mod h1:rcIxiG37BlQLB6FZfgdj9Fm7yjhRQd3l+5o7J0QPAk4= github.com/git-pkgs/pom v0.1.5 h1:TGT8Az2OMxGWsXnSagtUMGzZm7Oax8HrSCteA+mi0qY= @@ -424,8 +422,8 @@ github.com/kisielk/errcheck v1.9.0 h1:9xt1zI9EBfcYBvdU1nVrzMzzUPUtPKs9bVSIM3TAb3 github.com/kisielk/errcheck v1.9.0/go.mod h1:kQxWMMVZgIkDq7U8xtG/n2juOjbLgZtedi0D+/VL/i8= github.com/kkHAIKE/contextcheck v1.1.6 h1:7HIyRcnyzxL9Lz06NGhiKvenXq7Zw6Q0UQu/ttjfJCE= github.com/kkHAIKE/contextcheck v1.1.6/go.mod h1:3dDbMRNBFaq8HFXWC1JyvDSPm43CmE6IuHam8Wr0rkg= -github.com/klauspost/compress v1.19.0 h1:sXLILfc9jV2QYWkzFOPWStmcUVH2RHEB1JCdY2oVvCQ= -github.com/klauspost/compress v1.19.0/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ= +github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo= +github.com/klauspost/compress v1.18.0/go.mod h1:2Pp+KzxcywXVXMr50+X0Q/Lsb43OQHYWRCY2AiWywWQ= github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= @@ -543,14 +541,14 @@ github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgm github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10/go.mod h1:t/avpk3KcrXxUnYOhZhMXJlSEyie6gQbtLq5NM3loB8= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4= -github.com/prometheus/client_golang v1.24.0 h1:5XStIklKuAtJSNpdD3s8XJj/Yv78IQmE1kbNk87JrAI= -github.com/prometheus/client_golang v1.24.0/go.mod h1:QcsNdotprC2nS4BTM2ucbcqxd2CeXTEa9jW7zHO9iDE= +github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o= +github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg= github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk= github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE= -github.com/prometheus/common v0.70.0 h1:bcpru3tWPVnxGnETLgOV5jbp/JRXgYEyv65CuBLAMMI= -github.com/prometheus/common v0.70.0/go.mod h1:S/SFasQmgGiYH6C81LKCtYa8QACgthGg5zxL2udV7SY= -github.com/prometheus/procfs v0.21.1 h1:GljZCt+zSTS+NZq88cyQ1LjZ+RCHp3uVuabBWA5+OJI= -github.com/prometheus/procfs v0.21.1/go.mod h1:aB55Cww9pdSJVHk0hUf0inxWyyjPogFIjmHKYgMKmtY= +github.com/prometheus/common v0.67.5 h1:pIgK94WWlQt1WLwAC5j2ynLaBRDiinoAb86HZHTUGI4= +github.com/prometheus/common v0.67.5/go.mod h1:SjE/0MzDEEAyrdr5Gqc6G+sXI67maCxzaT3A2+HqjUw= +github.com/prometheus/procfs v0.20.1 h1:XwbrGOIplXW/AU3YhIhLODXMJYyC1isLFfYCsTEycfc= +github.com/prometheus/procfs v0.20.1/go.mod h1:o9EMBZGRyvDrSPH1RqdxhojkuXstoe4UlK79eF5TGGo= github.com/quasilyte/go-ruleguard v0.4.5 h1:AGY0tiOT5hJX9BTdx/xBdoCubQUAE2grkqY2lSwvZcA= github.com/quasilyte/go-ruleguard v0.4.5/go.mod h1:Vl05zJ538vcEEwu16V/Hdu7IYZWyKSwIy4c88Ro1kRE= github.com/quasilyte/go-ruleguard/dsl v0.3.23 h1:lxjt5B6ZCiBeeNO8/oQsegE6fLeCzuMRoVWSkXC4uvY= @@ -728,8 +726,8 @@ go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0= go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y= go.uber.org/zap v1.27.1 h1:08RqriUEv8+ArZRYSTXy1LeBScaMpVSTBhCeaZYfMYc= go.uber.org/zap v1.27.1/go.mod h1:GB2qFLM7cTU87MWRP2mPIjqfIDnGu+VIO4V/SdhGo2E= -go.yaml.in/yaml/v2 v2.4.4 h1:tuyd0P+2Ont/d6e2rl3be67goVK4R6deVxCUX5vyPaQ= -go.yaml.in/yaml/v2 v2.4.4/go.mod h1:gMZqIpDtDqOfM0uNfy0SkpRhvUryYH0Z6wdMYcacYXQ= +go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0= +go.yaml.in/yaml/v2 v2.4.3/go.mod h1:zSxWcmIDjOzPXpjlTTbAsKokqkDNAVtZO0WOMiT90s8= go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc= go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg= gocloud.dev v0.46.0 h1:niIuZwSjMtBx8K+ITB2s5kZullB13PGOS2ZoQPZxQ4Q= @@ -809,8 +807,8 @@ golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs= -golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= +golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw= +golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= @@ -906,8 +904,8 @@ modernc.org/opt v0.2.0 h1:tGyef5ApycA7FSEOMraay9SaTk5zmbx7Tu+cJs4QKZg= modernc.org/opt v0.2.0/go.mod h1:03fq9lsNfvkYSfxrfUhZCWPk1lm4cq4N+Bh//bEtgns= modernc.org/sortutil v1.2.1 h1:+xyoGf15mM3NMlPDnFqrteY07klSFxLElE2PVuWIJ7w= modernc.org/sortutil v1.2.1/go.mod h1:7ZI3a3REbai7gzCLcotuw9AC4VZVpYMjDzETGsSMqJE= -modernc.org/sqlite v1.55.0 h1:hIFh0MCH0rGinQ/4KYb5/UbCkRkb+UP+OkLCVWa5MTM= -modernc.org/sqlite v1.55.0/go.mod h1:4ntCLuNmnH8+GNqjka1wNg7KJd5/Hi5FYp8K+XQ7GZw= +modernc.org/sqlite v1.54.0 h1:JCxR4qwkJvOaqAoYcgDoO25Nc+ROg6EJ2LfBVzdrgog= +modernc.org/sqlite v1.54.0/go.mod h1:4ntCLuNmnH8+GNqjka1wNg7KJd5/Hi5FYp8K+XQ7GZw= modernc.org/strutil v1.2.1 h1:UneZBkQA+DX2Rp35KcM69cSsNES9ly8mQWD71HKlOA0= modernc.org/strutil v1.2.1/go.mod h1:EHkiggD70koQxjVdSBM3JKM7k6L0FbGE5eymy9i3B9A= modernc.org/token v1.1.0 h1:Xl7Ap9dKaEs5kLoOQeQmPWevfnk/DM5qcLcYlA8ys6Y= diff --git a/internal/server/browse.go b/internal/server/browse.go index 56aa1c5..504f5f1 100644 --- a/internal/server/browse.go +++ b/internal/server/browse.go @@ -1,7 +1,6 @@ package server import ( - "bufio" "encoding/json" "fmt" "io" @@ -11,22 +10,29 @@ import ( "github.com/git-pkgs/archives" "github.com/git-pkgs/archives/diff" - "github.com/git-pkgs/magic" "github.com/git-pkgs/proxy/internal/database" "github.com/git-pkgs/purl" "github.com/go-chi/chi/v5" ) -const ( - contentTypePlainText = "text/plain; charset=utf-8" - browseSniffSize = 512 -) +const contentTypePlainText = "text/plain; charset=utf-8" // maxBrowseArchiveSize caps how much data openArchive will buffer for // prefix detection. Artifacts larger than this are rejected to prevent // memory exhaustion from a single request. const maxBrowseArchiveSize = 512 << 20 // 512 MB +// archiveFilename returns a filename suitable for archive format detection. +// Some ecosystems (e.g. composer) store artifacts with bare hash filenames +// that have no extension. This adds .zip when the original has no extension +// and the content is likely a zip archive. +func archiveFilename(filename string) string { + if path.Ext(filename) == "" { + return filename + ".zip" + } + return filename +} + // detectSingleRootDir returns the single top-level directory name if all files // in the archive live under one common directory (e.g. GitHub zipballs use // "repo-hash/"). Returns "" if there's no single root or the archive is flat. @@ -60,6 +66,8 @@ func detectSingleRootDir(reader archives.Reader) string { // and stripping a single top-level directory prefix (like GitHub zipballs). // For npm, the hardcoded "package/" prefix takes precedence. func openArchive(filename string, content io.Reader, ecosystem string) (archives.Reader, error) { //nolint:ireturn // wraps multiple archive implementations + fname := archiveFilename(filename) + limited := io.LimitReader(content, maxBrowseArchiveSize+1) data, err := io.ReadAll(limited) if err != nil { @@ -70,17 +78,17 @@ func openArchive(filename string, content io.Reader, ecosystem string) (archives } if ecosystem == "npm" { - return archives.OpenBytesWithPrefix(filename, data, "package/") + return archives.OpenBytesWithPrefix(fname, data, "package/") } - probe, err := archives.OpenBytes(filename, data) + probe, err := archives.OpenBytes(fname, data) if err != nil { return nil, err } prefix := detectSingleRootDir(probe) _ = probe.Close() - return archives.OpenBytesWithPrefix(filename, data, prefix) + return archives.OpenBytesWithPrefix(fname, data, prefix) } // BrowseListResponse contains the file listing for a directory in an archives. @@ -353,14 +361,7 @@ func (s *Server) browseFile(w http.ResponseWriter, r *http.Request, ecosystem, n } defer func() { _ = fileReader.Close() }() - contentType, knownPath := detectContentTypeFromPath(filePath) - var content io.Reader = fileReader - if !knownPath { - bufferedFile := bufio.NewReaderSize(fileReader, browseSniffSize) - prefix, _ := bufferedFile.Peek(browseSniffSize) - contentType = detectContentTypeFromPrefix(prefix) - content = bufferedFile - } + contentType := detectContentType(filePath) w.Header().Set("Content-Type", contentType) w.Header().Set("Content-Security-Policy", "sandbox") w.Header().Set("X-Content-Type-Options", "nosniff") @@ -369,103 +370,85 @@ func (s *Server) browseFile(w http.ResponseWriter, r *http.Request, ecosystem, n w.Header().Set("Content-Disposition", fmt.Sprintf("inline; filename=%q", filename)) // Stream the file - _, _ = io.Copy(w, content) + _, _ = io.Copy(w, fileReader) } -func detectContentTypeFromPath(filename string) (string, bool) { +// detectContentType returns an appropriate content type based on file extension. +func detectContentType(filename string) string { ext := strings.ToLower(path.Ext(filename)) switch ext { // Text formats case ".txt", ".md", ".markdown": - return contentTypePlainText, true + return contentTypePlainText case ".html", ".htm", ".xhtml": - return contentTypePlainText, true + return contentTypePlainText case ".css": - return "text/css; charset=utf-8", true + return "text/css; charset=utf-8" case ".js", ".mjs": - return "application/javascript; charset=utf-8", true + return "application/javascript; charset=utf-8" case ".json": - return "application/json; charset=utf-8", true + return "application/json; charset=utf-8" case ".xml": - return "application/xml; charset=utf-8", true + return "application/xml; charset=utf-8" case ".yaml", ".yml": - return "text/yaml; charset=utf-8", true + return "text/yaml; charset=utf-8" case ".toml": - return "text/toml; charset=utf-8", true + return "text/toml; charset=utf-8" // Programming languages case ".go": - return "text/x-go; charset=utf-8", true + return "text/x-go; charset=utf-8" case ".rs": - return "text/x-rust; charset=utf-8", true + return "text/x-rust; charset=utf-8" case ".py": - return "text/x-python; charset=utf-8", true + return "text/x-python; charset=utf-8" case ".rb": - return "text/x-ruby; charset=utf-8", true + return "text/x-ruby; charset=utf-8" case ".java": - return "text/x-java; charset=utf-8", true + return "text/x-java; charset=utf-8" case ".c", ".h": - return "text/x-c; charset=utf-8", true + return "text/x-c; charset=utf-8" case ".cpp", ".cc", ".cxx", ".hpp": - return "text/x-c++; charset=utf-8", true + return "text/x-c++; charset=utf-8" case ".ts": - return "text/typescript; charset=utf-8", true + return "text/typescript; charset=utf-8" case ".tsx": - return "text/tsx; charset=utf-8", true + return "text/tsx; charset=utf-8" case ".jsx": - return "text/jsx; charset=utf-8", true + return "text/jsx; charset=utf-8" case ".php": - return "text/x-php; charset=utf-8", true + return "text/x-php; charset=utf-8" // Config files case ".conf", ".config", ".ini": - return contentTypePlainText, true + return contentTypePlainText case ".sh", ".bash": - return "text/x-shellscript; charset=utf-8", true + return "text/x-shellscript; charset=utf-8" case ".dockerfile": - return "text/x-dockerfile; charset=utf-8", true + return "text/x-dockerfile; charset=utf-8" // Images case ".png": - return "image/png", true + return "image/png" case ".jpg", ".jpeg": - return "image/jpeg", true + return "image/jpeg" case ".gif": - return "image/gif", true + return "image/gif" case ".svg": - return contentTypePlainText, true + return contentTypePlainText case ".ico": - return "image/x-icon", true + return "image/x-icon" // Archives case ".zip", ".tar", ".gz", ".bz2", ".xz": - return "application/octet-stream", true + return "application/octet-stream" default: + // Try to detect if it looks like text if isLikelyText(filename) { - return contentTypePlainText, true + return contentTypePlainText } - return "", false - } -} - -func detectContentTypeFromPrefix(prefix []byte) string { - result := magic.DetectPrefix(prefix) - if result.Kind == magic.KindText { - return contentTypePlainText - } - - switch result.Format { - case "png": - return "image/png" - case "jpeg": - return "image/jpeg" - case "gif": - return "image/gif" - case "pdf": - return "application/pdf" - default: return "application/octet-stream" } } diff --git a/internal/server/browse_bench_test.go b/internal/server/browse_bench_test.go index 840bc75..03f3f02 100644 --- a/internal/server/browse_bench_test.go +++ b/internal/server/browse_bench_test.go @@ -55,35 +55,3 @@ func BenchmarkOpenArchive(b *testing.B) { }) } } - -func BenchmarkDetectContentType(b *testing.B) { - cases := []struct { - name string - filename string - prefix []byte - knownPath bool - }{ - {"known-path", "README.md", nil, true}, - {"text-prefix", "artifact", bytes.Repeat([]byte("a"), browseSniffSize), false}, - {"png-prefix", "artifact", append([]byte("\x89PNG\r\n\x1a\n"), make([]byte, browseSniffSize-8)...), false}, - } - - for _, tc := range cases { - b.Run(tc.name, func(b *testing.B) { - b.ReportAllocs() - var contentType string - if tc.knownPath { - for b.Loop() { - contentType, _ = detectContentTypeFromPath(tc.filename) - } - } else { - for b.Loop() { - contentType = detectContentTypeFromPrefix(tc.prefix) - } - } - if contentType == "" { - b.Fatal("empty content type") - } - }) - } -} diff --git a/internal/server/browse_test.go b/internal/server/browse_test.go index 5240a92..f1fb993 100644 --- a/internal/server/browse_test.go +++ b/internal/server/browse_test.go @@ -137,44 +137,29 @@ func TestHandleBrowseFile(t *testing.T) { t.Fatalf("failed to upsert artifact: %v", err) } - files := []struct { - path string - content string - contentType string - }{ - {"README.md", "# Test Package\n", contentTypePlainText}, - {"notes.data", "short text\n", contentTypePlainText}, - {"logo", "\x89PNG\r\n\x1a\nimage data", "image/png"}, - {"page", "", contentTypePlainText}, - {"misleading.txt", "\x89PNG\r\n\x1a\nimage data", contentTypePlainText}, - } - for _, file := range files { - t.Run(file.path, func(t *testing.T) { - req := httptest.NewRequest("GET", "/ui/api/browse/npm/test-browse/1.0.0/file/"+file.path, nil) - w := httptest.NewRecorder() - ts.handler.ServeHTTP(w, req) + // Test fetching a file + req := httptest.NewRequest("GET", "/ui/api/browse/npm/test-browse/1.0.0/file/README.md", nil) + w := httptest.NewRecorder() + ts.handler.ServeHTTP(w, req) - if w.Code != http.StatusOK { - t.Fatalf("expected status 200, got %d: %s", w.Code, w.Body.String()) - } - if w.Body.String() != file.content { - t.Errorf("unexpected file content: %q", w.Body.String()) - } - if got := w.Header().Get("Content-Type"); got != file.contentType { - t.Errorf("Content-Type = %q, want %q", got, file.contentType) - } - if got := w.Header().Get("Content-Security-Policy"); got != "sandbox" { - t.Errorf("Content-Security-Policy = %q, want sandbox", got) - } - if got := w.Header().Get("X-Content-Type-Options"); got != "nosniff" { - t.Errorf("X-Content-Type-Options = %q, want nosniff", got) - } - }) + if w.Code != http.StatusOK { + t.Fatalf("expected status 200, got %d: %s", w.Code, w.Body.String()) + } + + body := w.Body.String() + if body != "# Test Package\n" { + t.Errorf("unexpected file content: %q", body) + } + + // Check content type + contentType := w.Header().Get("Content-Type") + if contentType != contentTypePlainText { + t.Errorf("expected text/plain content type, got %q", contentType) } // Test fetching non-existent file - req := httptest.NewRequest("GET", "/ui/api/browse/npm/test-browse/1.0.0/file/nonexistent.txt", nil) - w := httptest.NewRecorder() + req = httptest.NewRequest("GET", "/ui/api/browse/npm/test-browse/1.0.0/file/nonexistent.txt", nil) + w = httptest.NewRecorder() ts.handler.ServeHTTP(w, req) if w.Code != http.StatusNotFound { @@ -182,52 +167,36 @@ func TestHandleBrowseFile(t *testing.T) { } } -func TestBrowseContentTypePolicy(t *testing.T) { +func TestDetectContentType(t *testing.T) { tests := []struct { - name string filename string - prefix []byte expectedCT string }{ - {"text extension", "file.txt", nil, contentTypePlainText}, - {"markdown extension", "file.md", nil, contentTypePlainText}, - {"JSON extension", "file.json", nil, "application/json; charset=utf-8"}, - {"JavaScript extension", "file.js", nil, "application/javascript; charset=utf-8"}, - {"Go extension", "file.go", nil, "text/x-go; charset=utf-8"}, - {"Python extension", "file.py", nil, "text/x-python; charset=utf-8"}, - {"Rust extension", "file.rs", nil, "text/x-rust; charset=utf-8"}, - {"HTML extension", "file.html", nil, contentTypePlainText}, - {"HTM extension", "file.htm", nil, contentTypePlainText}, - {"XHTML extension", "file.xhtml", nil, contentTypePlainText}, - {"SVG extension", "file.svg", nil, contentTypePlainText}, - {"PNG extension", "file.png", nil, "image/png"}, - {"JPEG extension", "file.jpg", nil, "image/jpeg"}, - {"README", "README", nil, contentTypePlainText}, - {"LICENSE", "LICENSE", nil, contentTypePlainText}, - {"Makefile", "Makefile", nil, contentTypePlainText}, - {"gitignore", ".gitignore", nil, contentTypePlainText}, - {"unknown empty", "file.bin", nil, "application/octet-stream"}, - {"extensionless PNG", "asset", []byte("\x89PNG\r\n\x1a\n"), "image/png"}, - {"extensionless JPEG", "asset", []byte("\xff\xd8\xff"), "image/jpeg"}, - {"extensionless GIF", "asset", []byte("GIF89a"), "image/gif"}, - {"extensionless PDF", "asset", []byte("%PDF-1.7"), "application/pdf"}, - {"extensionless text", "asset", []byte("plain text\n"), contentTypePlainText}, - {"extensionless HTML", "asset", []byte(""), contentTypePlainText}, - {"extensionless XML", "asset", []byte(""), contentTypePlainText}, - {"extensionless SVG", "asset", []byte(""), contentTypePlainText}, - {"extensionless ZIP", "asset", []byte("PK\x03\x04"), "application/octet-stream"}, - {"extensionless binary", "asset", []byte{0, 1, 2}, "application/octet-stream"}, - {"known path wins", "file.txt", []byte("\x89PNG\r\n\x1a\n"), contentTypePlainText}, + {"file.txt", contentTypePlainText}, + {"file.md", contentTypePlainText}, + {"file.json", "application/json; charset=utf-8"}, + {"file.js", "application/javascript; charset=utf-8"}, + {"file.go", "text/x-go; charset=utf-8"}, + {"file.py", "text/x-python; charset=utf-8"}, + {"file.rs", "text/x-rust; charset=utf-8"}, + {"file.html", contentTypePlainText}, + {"file.htm", contentTypePlainText}, + {"file.xhtml", contentTypePlainText}, + {"file.svg", contentTypePlainText}, + {"file.png", "image/png"}, + {"file.jpg", "image/jpeg"}, + {"README", contentTypePlainText}, + {"LICENSE", contentTypePlainText}, + {"Makefile", contentTypePlainText}, + {".gitignore", contentTypePlainText}, + {"file.bin", "application/octet-stream"}, } for _, tt := range tests { - t.Run(tt.name, func(t *testing.T) { - got, knownPath := detectContentTypeFromPath(tt.filename) - if !knownPath { - got = detectContentTypeFromPrefix(tt.prefix) - } + t.Run(tt.filename, func(t *testing.T) { + got := detectContentType(tt.filename) if got != tt.expectedCT { - t.Errorf("content type for %q with prefix %q = %q, want %q", tt.filename, tt.prefix, got, tt.expectedCT) + t.Errorf("detectContentType(%q) = %q, want %q", tt.filename, got, tt.expectedCT) } }) } @@ -286,10 +255,6 @@ func createTestArchive(t *testing.T) []byte { "package/lib/index.js": "module.exports = {};", "package/lib/helper.js": "module.exports.help = () => {};", "package/test/index.test.js": "// tests", - "package/notes.data": "short text\n", - "package/logo": "\x89PNG\r\n\x1a\nimage data", - "package/page": "", - "package/misleading.txt": "\x89PNG\r\n\x1a\nimage data", } for path, content := range files { @@ -644,19 +609,25 @@ func TestHandleComparePage(t *testing.T) { } } -func TestOpenArchiveDetectsExtensionlessTarGz(t *testing.T) { - reader, err := openArchive("artifact", bytes.NewReader(createTestArchive(t)), "npm") - if err != nil { - t.Fatalf("openArchive failed: %v", err) +func TestArchiveFilename(t *testing.T) { + tests := []struct { + input string + want string + }{ + {"package.tar.gz", "package.tar.gz"}, + {"d2e2f014ccd6ec9fae8dbe6336a4164346a2a856", "d2e2f014ccd6ec9fae8dbe6336a4164346a2a856.zip"}, + {"file.zip", "file.zip"}, + {"archive.tgz", "archive.tgz"}, + {"noext", "noext.zip"}, } - defer func() { _ = reader.Close() }() - files, err := reader.List() - if err != nil { - t.Fatalf("List failed: %v", err) - } - if len(files) == 0 { - t.Fatal("expected files in extensionless archive") + for _, tt := range tests { + t.Run(tt.input, func(t *testing.T) { + got := archiveFilename(tt.input) + if got != tt.want { + t.Errorf("archiveFilename(%q) = %q, want %q", tt.input, got, tt.want) + } + }) } }