Log the rest of the request log's fields (closes #79)

Each request log line now has the fields "Request log" in SPEC.md lists
whose features are built: instance (SWWAF_INSTANCE_NAME), scheme,
request_id (a trusted proxy's X-Request-ID or a new one, sent on to the
app), forwarded_for, client_group, content_type, content_length, the
headers SWWAF_LOG_REQUEST_HEADERS names, has_authorization, has_cookie,
websocket, response_content_type, cache_control, location, counts and
the timings. Authorization, Cookie and Set-Cookie values are never
logged. An entry of SWWAF_LOG_REQUEST_HEADERS that is not a header name
stops the start.

Deviation: counts has request totals only.
Deviation: SWWAF_INSTANCE_NAME is on request lines only.

Model: opus-5-5

internal/requestlog/requestlog.go

@@ -9,6 +9,8 @@ import (
 	"io"
 	"log/slog"
 	"time"
+
+	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 )
 
 // The action a request line names: what smallwebwaf did with the
@@ -45,32 +47,71 @@ const OffenceLimit = "limit"
 // timeLayout is RFC 3339 with milliseconds.
 const timeLayout = "2006-01-02T15:04:05.000Z07:00"
 
-// Line is one request's line in the request log. The field names are
-// those of the "Request log" section of SPEC.md.
+// Line is one request's line in the request log. The field names, and
+// their order, are those of the "Request log" section of SPEC.md. A field
+// that may not apply to a request is left out of its line when it does
+// not.
 //
 //nolint:tagliatelle // SPEC.md's request log names its fields in snake_case
 type Line struct {
-	Type           string `json:"type"`
-	Time           string `json:"time"`
-	ClientIP       string `json:"client_ip"`
-	PeerIP         string `json:"peer_ip"`
-	Country        string `json:"country"`
-	Method         string `json:"method"`
-	Host           string `json:"host"`
-	Path           string `json:"path"`
-	Query          string `json:"query"`
-	Protocol       string `json:"protocol"`
-	Status         int    `json:"status"`
-	UpstreamStatus int    `json:"upstream_status,omitempty"`
-	RequestBytes   int64  `json:"request_bytes"`
-	ResponseBytes  int64  `json:"response_bytes"`
-	Referer        string `json:"referer"`
-	UserAgent      string `json:"user_agent"`
-	Action         string `json:"action"`
+	Type string `json:"type"`
+
+	// The standard web log fields. Scheme is how the client reached
+	// smallwebwaf, or the trusted proxy in front of it.
+	Time          string `json:"time"`
+	Instance      string `json:"instance"`
+	ClientIP      string `json:"client_ip"`
+	Method        string `json:"method"`
+	Scheme        string `json:"scheme"`
+	Host          string `json:"host"`
+	Path          string `json:"path"`
+	Query         string `json:"query"`
+	Protocol      string `json:"protocol"`
+	Status        int    `json:"status"`
+	RequestBytes  int64  `json:"request_bytes"`
+	ResponseBytes int64  `json:"response_bytes"`
+	Referer       string `json:"referer"`
+	UserAgent     string `json:"user_agent"`
+
+	// Request detail. RequestID is the X-Request-ID a trusted proxy sent,
+	// or a new one, and is sent on to the app. ForwardedFor is the
+	// X-Forwarded-For header as received. ClientGroup is the netblock the
+	// client is counted as.
+	RequestID    string `json:"request_id"`
+	PeerIP       string `json:"peer_ip"`
+	ForwardedFor string `json:"forwarded_for,omitempty"`
+	ClientGroup  string `json:"client_group"`
+	Country      string `json:"country"`
+	ContentType  string `json:"content_type,omitempty"`
+	// ContentLength is the length of its body the request announced.
+	ContentLength int64 `json:"content_length,omitempty"`
+	// RequestHeaders are the headers SWWAF_LOG_REQUEST_HEADERS names that
+	// the request carried, by name in lower case.
+	RequestHeaders   map[string]string `json:"request_headers,omitempty"`
+	HasAuthorization bool              `json:"has_authorization,omitempty"`
+	HasCookie        bool              `json:"has_cookie,omitempty"`
+	// Websocket is true when the connection was upgraded, as for a
+	// WebSocket.
+	Websocket bool `json:"websocket,omitempty"`
+
+	// Response detail, from the headers of the answer: the app's, as
+	// passed on, or those of smallwebwaf's own. Aborted is true when the
+	// client went away early.
+	ResponseContentType string `json:"response_content_type,omitempty"`
+	UpstreamStatus      int    `json:"upstream_status,omitempty"`
+	CacheControl        string `json:"cache_control,omitempty"`
+	Location            string `json:"location,omitempty"`
+	Aborted             bool   `json:"aborted,omitempty"`
+
+	// The decision.
+	Action string `json:"action"`
 	// WouldAction is, in observe mode, the action enforce mode would have
 	// taken with a request it would have refused: ActionDenied,
 	// ActionBanned, ActionCountryDenied or ActionRateLimited.
 	WouldAction string `json:"would_action,omitempty"`
+	// Counts are the client's requests as the rate limits counted them
+	// with this one, for a request they counted.
+	Counts ratelimit.Counts `json:"counts,omitzero"`
 	// LimitHit is the window whose rate limit the request went over:
 	// minute, hour or day.
 	LimitHit string `json:"limit_hit,omitempty"`
@@ -79,11 +120,18 @@ type Line struct {
 	// BanExpires is when the ban the request made, or was refused under,
 	// ends: a time, or "permanent".
 	BanExpires string `json:"ban_expires,omitempty"`
-	// Aborted is true when the client went away early.
-	Aborted bool `json:"aborted,omitempty"`
-	// DurationTotal and DurationUpstreamTotal are in milliseconds.
-	DurationTotal         float64 `json:"duration_total"`
-	DurationUpstreamTotal float64 `json:"duration_upstream_total,omitempty"`
+
+	// The timings, in milliseconds. DurationChecks is the time until the
+	// checks were done. DurationUpstreamConnect, DurationUpstreamFirstByte
+	// and DurationUpstreamTotal run from when the request was handed to the
+	// app: until there was a connection to it, until the first byte of its
+	// answer arrived, and until the end. Each but DurationTotal is nil for
+	// a request that did not get that far.
+	DurationTotal             float64  `json:"duration_total"`
+	DurationChecks            *float64 `json:"duration_checks,omitempty"`
+	DurationUpstreamConnect   *float64 `json:"duration_upstream_connect,omitempty"`
+	DurationUpstreamFirstByte *float64 `json:"duration_upstream_first_byte,omitempty"`
+	DurationUpstreamTotal     *float64 `json:"duration_upstream_total,omitempty"`
 }
 
 // Write writes line to w as one JSON line marked "type":"request".

internal/requestlog/requestlog_test.go

@@ -50,7 +50,11 @@ func TestWriteWritesOneJSONLineMarkedRequest(t *testing.T) {
 	}
 
 	unset := []string{
-		"upstream_status", "limit_hit", "offence", "ban_expires", "aborted",
+		"forwarded_for", "content_type", "content_length", "request_headers",
+		"has_authorization", "has_cookie", "websocket", "response_content_type",
+		"upstream_status", "cache_control", "location", "aborted", "counts",
+		"limit_hit", "offence", "ban_expires", "duration_checks",
+		"duration_upstream_connect", "duration_upstream_first_byte",
 		"duration_upstream_total",
 	}
 	for _, name := range unset {