Merge pull request #1291 from morluto/fix/process-port-normalization-sentence-period

fix(process): normalize ports that end a sentence

docs/process-capture.md

@@ -112,8 +112,11 @@ same admitted PTY chunks rather than a second unbounded stream.
 
 Port normalization recognizes explicit `port`, `tcp_port`, `udp_port`, and
 `listen` fields, URL authorities, IP endpoints, and `localhost` endpoints, with
-ports from 0 through 65535. It preserves ordinary counters, dimensions, file
-line numbers, and ambiguous bare host labels. Use explicit literal `patterns`
+ports from 0 through 65535. A port may end a sentence, as in `port: 8080.`;
+a period followed by a letter or digit continues a decimal, version, or host
+name instead. Each PTY chunk is normalized on its own, so a port whose period
+ends the chunk is left unchanged because its continuation is not yet known. It preserves ordinary counters, dimensions, file line numbers,
+and ambiguous bare host labels. Use explicit literal `patterns`
 for a different application-specific spelling. Set `ports: false` to preserve
 all endpoint numbers in comparison text. Captures commit the port-normalization
 version so older broad numeric normalization cannot silently compare as the

src/domain/process/processScenario.ts

@@ -85,7 +85,7 @@ export const processComparisonContract = (
   limits: scenario.limits,
   normalization: scenario.normalization,
   ...(scenario.normalization.ports
-    ? { port_normalization_version: "contextual-endpoints-v1" }
+    ? { port_normalization_version: "contextual-endpoints-v2" }
     : {}),
 });
 

src/process/capture/ProcessNormalization.test.ts

@@ -99,6 +99,34 @@ it("normalizes only contextual ports before overlapping PID values and honors di
   ).toBe(input);
 });
 
+it("normalizes ports that end a sentence but not decimal or host continuations", () => {
+  const input = [
+    "Listening on port: 8080.",
+    "Server at http://localhost:8080. Ready",
+    "Bound [::1]:3000.",
+    "listen=9000.\n",
+    "port: 80.5 localhost:8080.5 localhost:8080.example.test",
+    "port: 8080.β localhost:8080.é port: 8080é",
+  ].join("\n");
+  expect(normalizeProcessText(input, scenario({}), "/temporary", rootPid)).toBe(
+    [
+      "Listening on port: <port>.",
+      "Server at http://localhost:<port>. Ready",
+      "Bound [::1]:<port>.",
+      "listen=<port>.\n",
+      "port: 80.5 localhost:8080.5 localhost:8080.example.test",
+      "port: 8080.β localhost:8080.é port: 8080é",
+    ].join("\n"),
+  );
+});
+
+it("keeps a port before a chunk-final period, whose continuation is unknown", () => {
+  for (const chunk of ["port: 80.", "http://localhost:8080.", "[::1]:3000."])
+    expect(
+      normalizeProcessText(chunk, scenario({}), "/temporary", rootPid),
+    ).toBe(chunk);
+});
+
 it("normalizes representative process identities and preserves null, zero, and unrelated numbers", () => {
   const before = JSON.stringify(samples);
   const normalized = normalizeProcessSamples(samples, scenario({}), rootPid);

src/process/capture/ProcessNormalization.ts

@@ -41,9 +41,14 @@ export const normalizeProcessText = (
   return normalized;
 };
 
+// A port may end a sentence, but a period followed by a letter, digit, or
+// underscore in any script continues a decimal, version, or host name and is
+// not a port boundary.
+// PTY chunks are normalized independently, so a period that ends the chunk
+// stays unnormalized: its continuation may arrive in the next chunk.
 const normalizePortTokens = (value: string): string => {
   const endpointNormalized = value.replaceAll(
-    /(\b[a-z][a-z0-9+.-]*:\/\/[^\s/?#"'<>]+|\blocalhost|\b(?:\d{1,3}\.){3}\d{1,3}|\[[\da-f:.%]+\]):(\d{1,5})(?![\w.@:])/giu,
+    /(\b[a-z][a-z0-9+.-]*:\/\/[^\s/?#"'<>]+|\blocalhost|\b(?:\d{1,3}\.){3}\d{1,3}|\[[\da-f:.%]+\]):(\d{1,5})(?![\p{L}\p{N}_@:]|\.(?:[\p{L}\p{N}_]|$))/giu,
     (match: string, endpoint: string, port: string) => {
       if (Number(port) > 65_535) return match;
       const isEndpoint = endpoint.includes("://")
@@ -54,7 +59,7 @@ const normalizePortTokens = (value: string): string => {
     },
   );
   return endpointNormalized.replaceAll(
-    /(\b(?:port|tcp_port|udp_port|listen)\b["']?\s*[:=]\s*)(\d{1,5})(?![\w.])/giu,
+    /(\b(?:port|tcp_port|udp_port|listen)\b["']?\s*[:=]\s*)(\d{1,5})(?![\p{L}\p{N}_]|\.(?:[\p{L}\p{N}_]|$))/giu,
     (match: string, prefix: string, port: string) =>
       Number(port) <= 65_535 ? `${prefix}<port>` : match,
   );

tests/boundary/process/processCaptureNormalization.test.ts

@@ -63,7 +63,7 @@ itWithCaptureCapability(
       ),
     ).toBe(true);
     expect(capture.manifest.comparison_contract).toMatchObject({
-      port_normalization_version: "contextual-endpoints-v1",
+      port_normalization_version: "contextual-endpoints-v2",
     });
     expect(capture.exit).toMatchObject({ code: 0, reason: "exited" });
     expect(capture.cleanup).toMatchObject({