// Command paramminer is a reference mitmux plugin - a Param Miner-style
// hidden parameter prober. For every captured GET request, sends a
// clean baseline resend (exact original, unmodified) plus one probe per
// candidate parameter name from a small built-in wordlist, each adding
// exactly that one query parameter. A probe whose response differs
// meaningfully from the baseline (different status, or a body length
// that differs by more than a small threshold) suggests the backend
// actually reads and acts on a parameter that was never part of the
// original request - the class of bug Param Miner exists to find.
// Matches are tagged "paramminer:hit" on the original entry.
//
// Deliberately GET-only and a modest ~40-entry wordlist, not the
// thousands of candidates and POST/JSON-body probing real Param Miner
// covers - see PLAN.md's plugin section for why a small, honest v1
// beats a slow one pretending to be exhaustive. Speaks the wire
// protocol directly rather than importing mitmux's own internal Go
// packages - see plugins/authcheck's package doc for why, and
// PLUGINS.md for the protocol this and any other plugin, in any
// language, follows.
package main

import (
	"bufio"
	"bytes"
	"encoding/json"
	"flag"
	"fmt"
	"log"
	"net"
	"net/http"
	"os"
	"path/filepath"
	"strings"
)

type request struct {
	Type      string `json:"type"`
	ID        int64  `json:"id,omitempty"`
	Scheme    string `json:"scheme,omitempty"`
	Host      string `json:"host,omitempty"`
	Raw       []byte `json:"raw,omitempty"`
	TagPlugin string `json:"tag_plugin,omitempty"`
	Tag       string `json:"tag,omitempty"`
	TagData   string `json:"tag_data,omitempty"`
}

type summary struct {
	ID       int64  `json:"id"`
	Method   string `json:"method"`
	Scheme   string `json:"scheme"`
	Host     string `json:"host"`
	Path     string `json:"path"`
	Source   string `json:"source"`
	RespSize int    `json:"resp_size"`
}

type entryDetail struct {
	summary
	StatusCode int    `json:"status_code"`
	RequestRaw []byte `json:"request_raw"`
}

type response struct {
	Type   string       `json:"type"`
	New    *summary     `json:"new,omitempty"`
	Detail *entryDetail `json:"detail,omitempty"`
	Error  string       `json:"error,omitempty"`
}

type client struct {
	conn net.Conn
	enc  *json.Encoder
	dec  *json.Decoder
}

func dial(path string) (*client, error) {
	conn, err := net.Dial("unix", path)
	if err != nil {
		return nil, err
	}
	return &client{conn: conn, enc: json.NewEncoder(conn), dec: json.NewDecoder(conn)}, nil
}

func (c *client) call(req request) (response, error) {
	if err := c.enc.Encode(req); err != nil {
		return response{}, err
	}
	var resp response
	if err := c.dec.Decode(&resp); err != nil {
		return response{}, err
	}
	if resp.Type == "error" {
		return response{}, fmt.Errorf("%s", resp.Error)
	}
	return resp, nil
}

func defaultSocketPath() string {
	if rt := os.Getenv("XDG_RUNTIME_DIR"); rt != "" {
		return filepath.Join(rt, "mitmux.sock")
	}
	cfg, err := os.UserConfigDir()
	if err != nil {
		return "mitmux.sock"
	}
	return filepath.Join(cfg, "mitmux", "mitmux.sock")
}

// candidates is a small, hand-picked set of parameter names real
// backends surprisingly often read even when they're never part of any
// documented or observed request - debug/internal switches, alternate
// output formats, and access-control shortcuts being the most common
// real findings this kind of probe turns up.
var candidates = []string{
	"debug", "test", "admin", "internal", "verbose", "trace",
	"format", "output", "callback", "jsonp",
	"redirect", "return", "return_url", "next", "url", "continue",
	"id", "user_id", "uid", "account_id",
	"role", "access", "level", "scope",
	"token", "api_key", "apikey", "key", "secret",
	"env", "environment", "stage", "staging", "preview",
	"force", "bypass", "skip_auth", "override", "unsafe",
}

// diffThreshold is the minimum absolute AND relative body-length
// difference from baseline before a probe counts as a hit - small
// enough to catch a real behavior change, large enough to shrug off a
// timestamp or request-id echoed back in an otherwise-identical body.
const (
	diffThresholdBytes   = 16
	diffThresholdPercent = 0.02
)

type hit struct {
	Parameter      string `json:"parameter"`
	BaselineStatus int    `json:"baseline_status"`
	BaselineLength int    `json:"baseline_length"`
	ProbeStatus    int    `json:"probe_status"`
	ProbeLength    int    `json:"probe_length"`
}

func main() {
	socketPath := flag.String("socket", "", "daemon control socket path (default: same as mitmux itself)")
	pluginName := flag.String("name", "paramminer", "name this plugin tags entries as")
	flag.Parse()

	path := *socketPath
	if path == "" {
		path = defaultSocketPath()
	}

	actor, err := dial(path)
	if err != nil {
		log.Fatalf("dial %s: %v", path, err)
	}
	defer actor.conn.Close()

	subConn, err := net.Dial("unix", path)
	if err != nil {
		log.Fatalf("dial %s (subscribe): %v", path, err)
	}
	defer subConn.Close()
	if err := json.NewEncoder(subConn).Encode(request{Type: "subscribe"}); err != nil {
		log.Fatalf("subscribe: %v", err)
	}

	// Probing the same endpoint every single time it's seen again would
	// flood a host with the same wordlist over and over for no new
	// information - an in-memory, run-lifetime dedup by method+scheme+
	// host+path is enough to keep this a one-time cost per endpoint.
	probed := map[string]bool{}

	log.Printf("paramminer: watching live traffic on %s", path)
	dec := json.NewDecoder(subConn)
	for {
		var resp response
		if err := dec.Decode(&resp); err != nil {
			log.Fatalf("subscribe feed closed: %v", err)
		}
		if resp.Type != "new" || resp.New == nil {
			continue
		}
		sum := *resp.New
		if sum.Source != "proxy" || sum.Method != "GET" {
			continue
		}
		key := sum.Method + " " + sum.Scheme + "://" + sum.Host + sum.Path
		if probed[key] {
			continue
		}
		probed[key] = true

		if err := probeEntry(actor, *pluginName, sum.ID); err != nil {
			log.Printf("entry #%d: %v", sum.ID, err)
		}
	}
}

func probeEntry(c *client, pluginName string, id int64) error {
	resp, err := c.call(request{Type: "get", ID: id})
	if err != nil {
		return fmt.Errorf("get: %w", err)
	}
	if resp.Detail == nil {
		return fmt.Errorf("get: no detail in response")
	}
	detail := *resp.Detail

	baseReq, err := http.ReadRequest(bufio.NewReader(bytes.NewReader(detail.RequestRaw)))
	if err != nil {
		return nil // not a well-formed request we can safely reparse - skip, not fatal
	}

	// A fresh baseline resend, not the originally captured response -
	// avoids comparing against a response that's stale relative to
	// whatever server-side state has changed since it was captured, and
	// keeps the comparison apples-to-apples with probes sent moments
	// later under the same conditions.
	baseline, err := resendWithQuery(c, detail.Scheme, detail.Host, baseReq, "")
	if err != nil {
		return fmt.Errorf("baseline resend: %w", err)
	}

	var hits []hit
	for _, param := range candidates {
		probeResp, err := resendWithQuery(c, detail.Scheme, detail.Host, baseReq, param)
		if err != nil {
			log.Printf("entry #%d probe %q: %v", id, param, err)
			continue
		}
		if isDifferent(baseline, probeResp) {
			hits = append(hits, hit{
				Parameter:      param,
				BaselineStatus: baseline.status,
				BaselineLength: baseline.length,
				ProbeStatus:    probeResp.status,
				ProbeLength:    probeResp.length,
			})
		}
	}

	if len(hits) == 0 {
		return nil
	}

	data, err := json.Marshal(hits)
	if err != nil {
		return fmt.Errorf("marshal hits: %w", err)
	}
	if _, err := c.call(request{Type: "tag_entry", ID: id, TagPlugin: pluginName, Tag: "paramminer:hit", TagData: string(data)}); err != nil {
		return fmt.Errorf("tag_entry: %w", err)
	}
	names := make([]string, len(hits))
	for i, h := range hits {
		names[i] = h.Parameter
	}
	log.Printf("#%d %s -> possible hidden parameter(s): %s", id, detail.Path, strings.Join(names, ", "))
	return nil
}

type probeResult struct {
	status int
	length int
}

// resendWithQuery clones baseReq, adds param=1 to its query string (a
// no-op empty param means "the clean baseline, no candidate added"),
// and resends it via the daemon's repeat primitive. Note for anyone
// reusing this pattern: Request.Write ignores the RequestURI field
// entirely (verified directly - confirmed empty/stale RequestURI still
// produces the correct line, since Write derives it from req.URL, not
// that field) and silently adds a default User-Agent if the cloned
// request didn't already have one. Both baseline and every probe get
// the same treatment, so it can't cause a false diff between them -
// just a known way this resend isn't byte-for-byte identical to the
// original beyond the one intentional change.
func resendWithQuery(c *client, scheme, host string, baseReq *http.Request, param string) (probeResult, error) {
	u := *baseReq.URL
	if param != "" {
		q := u.Query()
		q.Set(param, "1")
		u.RawQuery = q.Encode()
	}

	req2 := baseReq.Clone(baseReq.Context())
	req2.URL = &u

	var buf bytes.Buffer
	if err := req2.Write(&buf); err != nil {
		return probeResult{}, fmt.Errorf("rebuild request: %w", err)
	}

	resp, err := c.call(request{Type: "repeat", Scheme: scheme, Host: host, Raw: buf.Bytes()})
	if err != nil {
		return probeResult{}, fmt.Errorf("repeat: %w", err)
	}
	if resp.Detail == nil {
		return probeResult{}, fmt.Errorf("repeat: no detail in response")
	}
	return probeResult{status: resp.Detail.StatusCode, length: resp.Detail.RespSize}, nil
}

func isDifferent(baseline, probe probeResult) bool {
	if baseline.status != probe.status {
		return true
	}
	diff := probe.length - baseline.length
	if diff < 0 {
		diff = -diff
	}
	if diff < diffThresholdBytes {
		return false
	}
	if baseline.length == 0 {
		return diff > 0
	}
	return float64(diff)/float64(baseline.length) >= diffThresholdPercent
}