diff --git a/go.mod b/go.mod index c7788c6..ae5fc68 100644 --- a/go.mod +++ b/go.mod @@ -20,6 +20,8 @@ require ( github.com/clipperhouse/displaywidth v0.4.1 // indirect github.com/clipperhouse/stringish v0.1.1 // indirect github.com/clipperhouse/uax29/v2 v2.3.0 // indirect + github.com/dustin/go-humanize v1.0.1 // indirect + github.com/google/uuid v1.6.0 // indirect github.com/inconshreveable/mousetrap v1.1.0 // indirect github.com/lucasb-eyer/go-colorful v1.3.0 // indirect github.com/mattn/go-runewidth v0.0.19 // indirect @@ -28,10 +30,17 @@ require ( github.com/muesli/mango-cobra v1.2.0 // indirect github.com/muesli/mango-pflag v0.1.0 // indirect github.com/muesli/roff v0.1.0 // indirect + github.com/ncruces/go-strftime v1.0.0 // indirect + github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect github.com/rivo/uniseg v0.4.7 // indirect github.com/spf13/pflag v1.0.9 // indirect + github.com/tamnd/any-cli v0.4.0 // indirect github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e // indirect - golang.org/x/sync v0.17.0 // indirect - golang.org/x/sys v0.37.0 // indirect + golang.org/x/sync v0.20.0 // indirect + golang.org/x/sys v0.42.0 // indirect golang.org/x/text v0.24.0 // indirect + modernc.org/libc v1.72.3 // indirect + modernc.org/mathutil v1.7.1 // indirect + modernc.org/memory v1.11.0 // indirect + modernc.org/sqlite v1.52.0 // indirect ) diff --git a/go.sum b/go.sum index e7d4564..c5f139c 100644 --- a/go.sum +++ b/go.sum @@ -29,6 +29,10 @@ github.com/clipperhouse/uax29/v2 v2.3.0/go.mod h1:Wn1g7MK6OoeDT0vL+Q0SQLDz/KpfsV github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= +github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY= +github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto= +github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= +github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8= github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= github.com/lucasb-eyer/go-colorful v1.3.0 h1:2/yBRLdWBZKrf7gB40FoiKfAWYQ0lqNcbuQwVHXptag= @@ -47,8 +51,12 @@ github.com/muesli/mango-pflag v0.1.0 h1:UADqbYgpUyRoBja3g6LUL+3LErjpsOwaC9ywvBWe github.com/muesli/mango-pflag v0.1.0/go.mod h1:YEQomTxaCUp8PrbhFh10UfbhbQrM/xJ4i2PB8VTLLW0= github.com/muesli/roff v0.1.0 h1:YD0lalCotmYuF5HhZliKWlIx7IEhiXeSfq7hNjFqGF8= github.com/muesli/roff v0.1.0/go.mod h1:pjAHQM9hdUUwm/krAfrLGgJkXJ+YuhtsfZ42kieB2Ig= +github.com/ncruces/go-strftime v1.0.0 h1:HMFp8mLCTPp341M/ZnA4qaf7ZlsbTc+miZjCLOFAw7w= +github.com/ncruces/go-strftime v1.0.0/go.mod h1:Fwc5htZGVVkseilnfgOVb9mKy6w1naJmn9CehxcKcls= 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/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE= +github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo= github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ= github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88= github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM= @@ -58,6 +66,8 @@ github.com/spf13/pflag v1.0.9 h1:9exaQaMOCwffKiiiYk6/BndUBv+iRViNW+4lEMi0PvY= github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA= github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= +github.com/tamnd/any-cli v0.4.0 h1:ngyRJBvjZ2X1iBlwlmDLvY2S9aQWlDjVE7CiOwxtt5Y= +github.com/tamnd/any-cli v0.4.0/go.mod h1:lns3VfQVrC9hMy7YKBzIQoYpobnfSDIzJ8c27H2ILmk= github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavMF/ppJZNG9ZpyihvCd0w101no= github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM= go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg= @@ -65,10 +75,22 @@ golang.org/x/exp v0.0.0-20231006140011-7918f672742d h1:jtJma62tbqLibJ5sFQz8bKtEM golang.org/x/exp v0.0.0-20231006140011-7918f672742d/go.mod h1:ldy0pHrwJyGW56pPQzzkH36rKxoZW1tw7ZJpeKx+hdo= golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug= golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI= +golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4= +golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0= golang.org/x/sys v0.37.0 h1:fdNQudmxPjkdUTPnLn5mdQv7Zwvbvpaxqs831goi9kQ= golang.org/x/sys v0.37.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks= +golang.org/x/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo= +golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= golang.org/x/text v0.24.0 h1:dd5Bzh4yt5KYA8f9CJHCP4FB4D51c2c6JvN37xJJkJ0= golang.org/x/text v0.24.0/go.mod h1:L8rBsPeo2pSS+xqN0d5u2ikmjtmoJbDBT1b7nHvFCdU= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +modernc.org/libc v1.72.3 h1:ZnDF4tXn4NBXFutMMQC4vtbTFSXhhKzR73fv0beZEAU= +modernc.org/libc v1.72.3/go.mod h1:dn0dZNnnn1clLyvRxLxYExxiKRZIRENOfqQ8XEeg4Qs= +modernc.org/mathutil v1.7.1 h1:GCZVGXdaN8gTqB1Mf/usp1Y/hSqgI2vAGGP4jZMCxOU= +modernc.org/mathutil v1.7.1/go.mod h1:4p5IwJITfppl0G4sUEDtCr4DthTaT47/N3aT6MhfgJg= +modernc.org/memory v1.11.0 h1:o4QC8aMQzmcwCK3t3Ux/ZHmwFPzE6hf2Y5LbkRs+hbI= +modernc.org/memory v1.11.0/go.mod h1:/JP4VbVC+K5sU2wZi9bHoq2MAkCnrt2r98UGeSK7Mjw= +modernc.org/sqlite v1.52.0 h1:p4dhYh2tXZCiyaqHwRVJDjIGKWyXayiQpThxgDzJaxo= +modernc.org/sqlite v1.52.0/go.mod h1:tcNzv5p84E0skkmJn038y+hWJbLQXQqEnQfeh5r2JLM= diff --git a/hupu/domain.go b/hupu/domain.go new file mode 100644 index 0000000..635c2bb --- /dev/null +++ b/hupu/domain.go @@ -0,0 +1,167 @@ +package hupu + +import ( + "context" + "fmt" + "net/url" + "regexp" + "strings" + + "github.com/tamnd/any-cli/kit" + "github.com/tamnd/any-cli/kit/errs" +) + +// domain.go exposes hupu as a kit Domain: a driver that a multi-domain +// host enables with a single blank import, +// +// import _ "github.com/tamnd/hupu-cli/hupu" +// +// The init below registers it; the host then dereferences hupu:// URIs by +// routing to the operations Register installs. +func init() { kit.Register(Domain{}) } + +// Domain is the hupu kit driver. It carries no state. +type Domain struct{} + +// Info describes the scheme, the hostnames a pasted link is matched against, +// and the identity reused for the binary's help and version. +func (Domain) Info() kit.DomainInfo { + return kit.DomainInfo{ + Scheme: "hupu", + Hosts: []string{"bbs.hupu.com"}, + Identity: kit.Identity{ + Binary: "hupu", + Short: "A command line for Hupu sports forum.", + Long: `A command line for Hupu sports forum. + +hupu reads public Hupu BBS data over plain HTTPS, shapes it into +clean records, and prints output that pipes into the rest of your tools. +No API key, nothing to run alongside it.`, + Site: "bbs.hupu.com", + Repo: "https://github.com/tamnd/hupu-cli", + }, + } +} + +// Register installs the client factory and every operation onto app. +func (Domain) Register(app *kit.App) { + app.SetClient(newKitClient) + + // hot: list the current hot threads from the BBS home page. + kit.Handle(app, kit.OpMeta{ + Name: "hot", + Group: "read", + List: true, + Summary: "List hot BBS posts", + URIType: "post", + }, listHot) + + // search: full-text search via the mobile API. + kit.Handle(app, kit.OpMeta{ + Name: "search", + Group: "read", + List: true, + Summary: "Search BBS posts", + URIType: "post", + Args: []kit.Arg{{Name: "query", Help: "search query"}}, + }, listSearch) +} + +// newKitClient builds the client from the kit-resolved config. +func newKitClient(_ context.Context, cfg kit.Config) (any, error) { + c := DefaultConfig() + if cfg.UserAgent != "" { + c.UserAgent = cfg.UserAgent + } + if cfg.Rate > 0 { + c.Rate = cfg.Rate + } + if cfg.Retries > 0 { + c.Retries = cfg.Retries + } + if cfg.Timeout > 0 { + c.Timeout = cfg.Timeout + } + return NewClient(c), nil +} + +// --- inputs --- + +type hotInput struct { + Limit int `kit:"flag,inherit" help:"max results"` + Client *Client `kit:"inject"` +} + +type searchInput struct { + Query string `kit:"arg" help:"search query"` + Limit int `kit:"flag,inherit" help:"max results"` + Client *Client `kit:"inject"` +} + +// --- handlers --- + +func listHot(ctx context.Context, in hotInput, emit func(*Post) error) error { + posts, err := in.Client.Hot(ctx, in.Limit) + if err != nil { + return err + } + for i := range posts { + if err := emit(&posts[i]); err != nil { + return err + } + } + return nil +} + +func listSearch(ctx context.Context, in searchInput, emit func(*Post) error) error { + if strings.TrimSpace(in.Query) == "" { + return errs.Usage("query is required") + } + posts, err := in.Client.Search(ctx, in.Query, in.Limit) + if err != nil { + return err + } + for i := range posts { + if err := emit(&posts[i]); err != nil { + return err + } + } + return nil +} + +// --- Resolver: pure string functions, no network --- + +// tidRE matches a numeric thread id in a URL path segment or bare string. +var tidRE = regexp.MustCompile(`\b(\d+)\b`) + +// Classify turns a post URL or bare thread ID into the canonical (type, id). +func (Domain) Classify(input string) (uriType, id string, err error) { + id = postID(input) + if id == "" { + return "", "", errs.Usage("unrecognized hupu reference: %q", input) + } + return "post", id, nil +} + +// Locate is the inverse: the live https URL for a (type, id). +func (Domain) Locate(uriType, id string) (string, error) { + if uriType != "post" { + return "", errs.Usage("hupu has no resource type %q", uriType) + } + return fmt.Sprintf("https://bbs.hupu.com/%s.html", id), nil +} + +// postID extracts a numeric thread id from a full URL or a bare id string. +func postID(input string) string { + input = strings.TrimSpace(input) + if u, err := url.Parse(input); err == nil && (u.Scheme == "http" || u.Scheme == "https") { + if m := tidRE.FindStringSubmatch(u.Path); m != nil { + return m[1] + } + return "" + } + if m := tidRE.FindStringSubmatch(input); m != nil { + return m[1] + } + return "" +} diff --git a/hupu/domain_test.go b/hupu/domain_test.go new file mode 100644 index 0000000..97d1e1a --- /dev/null +++ b/hupu/domain_test.go @@ -0,0 +1,70 @@ +package hupu + +import ( + "testing" + + "github.com/tamnd/any-cli/kit" +) + +// These tests are offline: they exercise the kit domain's pure string functions +// and the host wiring, which need no network. + +func TestDomainInfo(t *testing.T) { + info := Domain{}.Info() + if info.Scheme != "hupu" { + t.Errorf("Scheme = %q, want hupu", info.Scheme) + } + if len(info.Hosts) == 0 || info.Hosts[0] != "bbs.hupu.com" { + t.Errorf("Hosts = %v, want [bbs.hupu.com]", info.Hosts) + } + if info.Identity.Binary != "hupu" { + t.Errorf("Identity.Binary = %q, want hupu", info.Identity.Binary) + } +} + +func TestClassify(t *testing.T) { + cases := []struct{ in, typ, id string }{ + {"123456789", "post", "123456789"}, + {"https://bbs.hupu.com/987654321.html", "post", "987654321"}, + } + for _, tc := range cases { + typ, id, err := Domain{}.Classify(tc.in) + if err != nil || typ != tc.typ || id != tc.id { + t.Errorf("Classify(%q) = (%q, %q, %v), want (%q, %q, nil)", + tc.in, typ, id, err, tc.typ, tc.id) + } + } +} + +func TestClassifyBad(t *testing.T) { + _, _, err := Domain{}.Classify("no-digits-here") + if err == nil { + t.Error("Classify(bad) expected error, got nil") + } +} + +func TestLocate(t *testing.T) { + got, err := Domain{}.Locate("post", "123456789") + want := "https://bbs.hupu.com/123456789.html" + if err != nil || got != want { + t.Errorf("Locate = (%q, %v), want (%q, nil)", got, err, want) + } +} + +func TestLocateBadType(t *testing.T) { + _, err := Domain{}.Locate("unknown", "123456789") + if err == nil { + t.Error("Locate(unknown) expected error, got nil") + } +} + +func TestResolveOn(t *testing.T) { + h, err := kit.Open() + if err != nil { + t.Fatal(err) + } + got, err := h.ResolveOn("hupu", "987654321") + if err != nil || got.String() != "hupu://post/987654321" { + t.Errorf("ResolveOn = (%q, %v), want hupu://post/987654321", got.String(), err) + } +} diff --git a/hupu/hupu.go b/hupu/hupu.go index 8d4795e..4ca7221 100644 --- a/hupu/hupu.go +++ b/hupu/hupu.go @@ -9,13 +9,18 @@ package hupu import ( "context" + "encoding/json" "fmt" "io" "net/http" + "net/url" "sync" "time" ) +// searchAPIURL is the mobile search API endpoint. +const searchAPIURL = "https://games.mobileapi.hupu.com/7.5.80/search/v2" + // DefaultUserAgent mimics a desktop Chrome browser. const DefaultUserAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36" @@ -131,6 +136,47 @@ func (c *Client) pace() { c.last = time.Now() } +// searchResp is the shape returned by the mobile search API. +type searchResp struct { + Data struct { + Thread struct { + List []struct { + TID int `json:"tid"` + Title string `json:"title"` + } `json:"list"` + } `json:"thread"` + } `json:"data"` +} + +// Search queries the Hupu mobile search API and returns matching posts. +// If limit <= 0, all results from the first page are returned. +func (c *Client) Search(ctx context.Context, query string, limit int) ([]Post, error) { + u := searchAPIURL + "?query=" + url.QueryEscape(query) + "&page=1&type=all" + body, err := c.get(ctx, u) + if err != nil { + return nil, fmt.Errorf("search: %w", err) + } + + var resp searchResp + if err := json.Unmarshal(body, &resp); err != nil { + return nil, fmt.Errorf("search decode: %w", err) + } + + var out []Post + for i, item := range resp.Data.Thread.List { + out = append(out, Post{ + Rank: i + 1, + ID: fmt.Sprintf("%d", item.TID), + Title: item.Title, + URL: "https://bbs.hupu.com/" + fmt.Sprintf("%d", item.TID) + ".html", + }) + if limit > 0 && len(out) >= limit { + break + } + } + return out, nil +} + func backoff(attempt int) time.Duration { d := time.Duration(attempt) * 500 * time.Millisecond if d > 5*time.Second { diff --git a/hupu/types.go b/hupu/types.go index a003908..a5df546 100644 --- a/hupu/types.go +++ b/hupu/types.go @@ -1,9 +1,9 @@ package hupu -// Post is a single discussion thread from the Hupu BBS homepage. +// Post is a single discussion thread from the Hupu BBS. type Post struct { - Rank int `json:"rank"` - ID string `json:"id"` - Title string `json:"title"` - URL string `json:"url"` + Rank int `json:"rank" table:"rank"` + ID string `json:"id" kit:"id" table:"id"` + Title string `json:"title" table:"title"` + URL string `json:"url" table:"url,url"` }