gitnexus 1.6.0 → 1.6.2-rc.1

package/dist/core/group/extractors/topic-patterns/go.js

@@ -0,0 +1,120 @@
+import Go from 'tree-sitter-go';
+import { compilePatterns } from '../tree-sitter-scanner.js';
+/**
+ * Go topic extraction patterns.
+ *
+ * Detects Sarama, segmentio/kafka-go and nats.go producer/consumer APIs:
+ *   - `X.ConsumePartition("topic", ...)`
+ *   - `sarama.ProducerMessage{Topic: "xxx"}`
+ *   - `kafka.Writer{Topic: "xxx"}` / `kafka.WriterConfig{Topic: ...}`
+ *   - `kafka.Reader{Topic: "xxx"}` / `kafka.ReaderConfig{Topic: ...}`
+ *   - `nc.Subscribe("topic", ...)` / `js.Subscribe("topic", ...)`
+ *   - `nc.Publish("topic", ...)` / `js.Publish("topic", ...)`
+ *
+ * Every query MUST bind `@value` to the topic literal node.
+ */
+const GO_TOPIC_SPEC = {
+    name: 'go-topic',
+    language: Go,
+    patterns: [
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'kafka',
+                confidence: 0.7,
+                symbolName: 'ConsumePartition',
+            },
+            query: `
+        (call_expression
+          function: (selector_expression
+            field: (field_identifier) @method (#eq? @method "ConsumePartition"))
+          arguments: (argument_list . (interpreted_string_literal) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'kafka',
+                confidence: 0.75,
+                symbolName: 'sarama.ProducerMessage',
+            },
+            query: `
+        (composite_literal
+          type: (qualified_type
+            package: (package_identifier) @pkg (#eq? @pkg "sarama")
+            name: (type_identifier) @ty (#eq? @ty "ProducerMessage"))
+          body: (literal_value
+            (keyed_element
+              (literal_element (identifier) @field (#eq? @field "Topic"))
+              (literal_element (interpreted_string_literal) @value))))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'kafka',
+                confidence: 0.75,
+                symbolName: 'kafka.Writer',
+            },
+            query: `
+        (composite_literal
+          type: (qualified_type
+            package: (package_identifier) @pkg (#eq? @pkg "kafka")
+            name: (type_identifier) @ty (#match? @ty "^(Writer|WriterConfig)$"))
+          body: (literal_value
+            (keyed_element
+              (literal_element (identifier) @field (#eq? @field "Topic"))
+              (literal_element (interpreted_string_literal) @value))))
+      `,
+        },
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'kafka',
+                confidence: 0.75,
+                symbolName: 'kafka.Reader',
+            },
+            query: `
+        (composite_literal
+          type: (qualified_type
+            package: (package_identifier) @pkg (#eq? @pkg "kafka")
+            name: (type_identifier) @ty (#match? @ty "^(Reader|ReaderConfig)$"))
+          body: (literal_value
+            (keyed_element
+              (literal_element (identifier) @field (#eq? @field "Topic"))
+              (literal_element (interpreted_string_literal) @value))))
+      `,
+        },
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'nats',
+                confidence: 0.8,
+                symbolName: 'nc.Subscribe',
+            },
+            query: `
+        (call_expression
+          function: (selector_expression
+            operand: (identifier) @obj (#match? @obj "^(nc|js)$")
+            field: (field_identifier) @method (#match? @method "^[Ss]ubscribe$"))
+          arguments: (argument_list . (interpreted_string_literal) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'nats',
+                confidence: 0.8,
+                symbolName: 'nc.Publish',
+            },
+            query: `
+        (call_expression
+          function: (selector_expression
+            operand: (identifier) @obj (#match? @obj "^(nc|js)$")
+            field: (field_identifier) @method (#match? @method "^[Pp]ublish$"))
+          arguments: (argument_list . (interpreted_string_literal) @value))
+      `,
+        },
+    ],
+};
+export const GO_TOPIC_PROVIDER = compilePatterns(GO_TOPIC_SPEC);

package/dist/core/group/extractors/topic-patterns/index.d.ts

@@ -0,0 +1,14 @@
+import type { CompiledPatterns } from '../tree-sitter-scanner.js';
+import type { TopicMeta } from './types.js';
+export type { TopicMeta, Broker } from './types.js';
+/**
+ * Glob pattern for files worth scanning. Kept here so adding a new
+ * language to the registry also widens the glob automatically via a
+ * single edit.
+ */
+export declare const TOPIC_SCAN_GLOB = "**/*.{ts,tsx,js,jsx,java,go,py}";
+/**
+ * Return the compiled provider registered for the given file's
+ * extension, or `undefined` if the extension is not registered.
+ */
+export declare function getProviderForFile(rel: string): CompiledPatterns<TopicMeta> | undefined;

package/dist/core/group/extractors/topic-patterns/index.js

@@ -0,0 +1,38 @@
+import * as path from 'node:path';
+import { JAVA_TOPIC_PROVIDER } from './java.js';
+import { GO_TOPIC_PROVIDER } from './go.js';
+import { PYTHON_TOPIC_PROVIDER } from './python.js';
+import { JAVASCRIPT_TOPIC_PROVIDER, TYPESCRIPT_TOPIC_PROVIDER, TSX_TOPIC_PROVIDER, } from './node.js';
+/**
+ * File-extension → compiled-plugin registry for topic extraction. The
+ * top-level orchestrator (`topic-extractor.ts`) looks up the plugin for
+ * each file it visits and delegates the scanning to `tree-sitter-scanner`.
+ *
+ * Keys are lowercase extensions including the leading dot. To add a new
+ * language, drop a `topic-patterns/<lang>.ts` that exports a compiled
+ * provider, import it here and register the extension(s). No edits to
+ * `topic-extractor.ts` are required.
+ */
+const REGISTRY = {
+    '.java': JAVA_TOPIC_PROVIDER,
+    '.go': GO_TOPIC_PROVIDER,
+    '.py': PYTHON_TOPIC_PROVIDER,
+    '.js': JAVASCRIPT_TOPIC_PROVIDER,
+    '.jsx': JAVASCRIPT_TOPIC_PROVIDER,
+    '.ts': TYPESCRIPT_TOPIC_PROVIDER,
+    '.tsx': TSX_TOPIC_PROVIDER,
+};
+/**
+ * Glob pattern for files worth scanning. Kept here so adding a new
+ * language to the registry also widens the glob automatically via a
+ * single edit.
+ */
+export const TOPIC_SCAN_GLOB = '**/*.{ts,tsx,js,jsx,java,go,py}';
+/**
+ * Return the compiled provider registered for the given file's
+ * extension, or `undefined` if the extension is not registered.
+ */
+export function getProviderForFile(rel) {
+    const ext = path.extname(rel).toLowerCase();
+    return REGISTRY[ext];
+}

package/dist/core/group/extractors/topic-patterns/java.d.ts

@@ -0,0 +1,2 @@
+import type { TopicMeta } from './types.js';
+export declare const JAVA_TOPIC_PROVIDER: import("../tree-sitter-scanner.js").CompiledPatterns<TopicMeta>;

package/dist/core/group/extractors/topic-patterns/java.js

@@ -0,0 +1,80 @@
+import Java from 'tree-sitter-java';
+import { compilePatterns } from '../tree-sitter-scanner.js';
+/**
+ * Java topic extraction patterns.
+ *
+ * Detects Kafka and RabbitMQ (Spring conventions) producer/consumer APIs:
+ *   - `@KafkaListener(topics = "xxx")`
+ *   - `@RabbitListener(queues = "xxx")`
+ *   - `kafkaTemplate.send("xxx", ...)`
+ *   - `rabbitTemplate.convertAndSend("xxx", ...)`
+ *
+ * Every query MUST bind `@value` to the topic literal node.
+ */
+const JAVA_TOPIC_SPEC = {
+    name: 'java-topic',
+    language: Java,
+    patterns: [
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'kafka',
+                confidence: 0.8,
+                symbolName: 'kafkaListener',
+            },
+            query: `
+        (annotation
+          name: (identifier) @name (#eq? @name "KafkaListener")
+          arguments: (annotation_argument_list
+            (element_value_pair
+              key: (identifier) @key (#eq? @key "topics")
+              value: (string_literal) @value)))
+      `,
+        },
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'rabbitmq',
+                confidence: 0.8,
+                symbolName: 'rabbitListener',
+            },
+            query: `
+        (annotation
+          name: (identifier) @name (#eq? @name "RabbitListener")
+          arguments: (annotation_argument_list
+            (element_value_pair
+              key: (identifier) @key (#eq? @key "queues")
+              value: (string_literal) @value)))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'kafka',
+                confidence: 0.8,
+                symbolName: 'kafkaTemplate.send',
+            },
+            query: `
+        (method_invocation
+          object: (identifier) @obj (#eq? @obj "kafkaTemplate")
+          name: (identifier) @method (#eq? @method "send")
+          arguments: (argument_list . (string_literal) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'rabbitmq',
+                confidence: 0.8,
+                symbolName: 'rabbitTemplate.convertAndSend',
+            },
+            query: `
+        (method_invocation
+          object: (identifier) @obj (#eq? @obj "rabbitTemplate")
+          name: (identifier) @method (#eq? @method "convertAndSend")
+          arguments: (argument_list . (string_literal) @value))
+      `,
+        },
+    ],
+};
+export const JAVA_TOPIC_PROVIDER = compilePatterns(JAVA_TOPIC_SPEC);

package/dist/core/group/extractors/topic-patterns/node.d.ts

@@ -0,0 +1,4 @@
+import type { TopicMeta } from './types.js';
+export declare const JAVASCRIPT_TOPIC_PROVIDER: import("../tree-sitter-scanner.js").CompiledPatterns<TopicMeta>;
+export declare const TYPESCRIPT_TOPIC_PROVIDER: import("../tree-sitter-scanner.js").CompiledPatterns<TopicMeta>;
+export declare const TSX_TOPIC_PROVIDER: import("../tree-sitter-scanner.js").CompiledPatterns<TopicMeta>;

package/dist/core/group/extractors/topic-patterns/node.js

@@ -0,0 +1,155 @@
+import JavaScript from 'tree-sitter-javascript';
+import TypeScript from 'tree-sitter-typescript';
+import { compilePatterns, } from '../tree-sitter-scanner.js';
+/**
+ * Node.js / TypeScript topic extraction patterns.
+ *
+ * Detects kafkajs, amqplib (RabbitMQ), and nats.js producer/consumer APIs:
+ *   - `producer.send({ topic: 'xxx', ... })` (kafkajs)
+ *   - `consumer.subscribe({ topic: 'xxx', ... })` (kafkajs)
+ *   - `channel.consume("queue", ...)` / `channel.publish(...)` / `channel.sendToQueue(...)`
+ *   - `nc.subscribe("topic")` / `js.subscribe("topic")`
+ *   - `nc.publish("topic", ...)` / `js.publish("topic", ...)`
+ *
+ * The JavaScript and TypeScript tree-sitter grammars share node type
+ * names for every construct we query here, so the pattern sources are
+ * defined once and compiled against each grammar variant. We export three
+ * providers because Parser.Query objects are NOT portable across grammar
+ * instances — `.js` files use the JavaScript grammar, `.ts` uses
+ * TypeScript.typescript, and `.tsx` uses TypeScript.tsx.
+ *
+ * Every query MUST bind `@value` to the topic literal node.
+ */
+const NODE_TOPIC_PATTERNS = [
+    {
+        meta: {
+            role: 'provider',
+            broker: 'kafka',
+            confidence: 0.8,
+            symbolName: 'producer.send',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#eq? @obj "producer")
+          property: (property_identifier) @prop (#eq? @prop "send"))
+        arguments: (arguments
+          (object
+            (pair
+              key: (property_identifier) @key (#eq? @key "topic")
+              value: [(string) (template_string)] @value))))
+    `,
+    },
+    {
+        meta: {
+            role: 'consumer',
+            broker: 'kafka',
+            confidence: 0.8,
+            symbolName: 'consumer.subscribe',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#eq? @obj "consumer")
+          property: (property_identifier) @prop (#eq? @prop "subscribe"))
+        arguments: (arguments
+          (object
+            (pair
+              key: (property_identifier) @key (#eq? @key "topic")
+              value: [(string) (template_string)] @value))))
+    `,
+    },
+    {
+        meta: {
+            role: 'consumer',
+            broker: 'rabbitmq',
+            confidence: 0.8,
+            symbolName: 'channel.consume',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#eq? @obj "channel")
+          property: (property_identifier) @prop (#eq? @prop "consume"))
+        arguments: (arguments . [(string) (template_string)] @value))
+    `,
+    },
+    {
+        meta: {
+            role: 'provider',
+            broker: 'rabbitmq',
+            confidence: 0.8,
+            symbolName: 'channel.publish',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#eq? @obj "channel")
+          property: (property_identifier) @prop (#eq? @prop "publish"))
+        arguments: (arguments . [(string) (template_string)] @value))
+    `,
+    },
+    {
+        meta: {
+            role: 'provider',
+            broker: 'rabbitmq',
+            confidence: 0.8,
+            symbolName: 'channel.sendToQueue',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#eq? @obj "channel")
+          property: (property_identifier) @prop (#eq? @prop "sendToQueue"))
+        arguments: (arguments . [(string) (template_string)] @value))
+    `,
+    },
+    {
+        meta: {
+            role: 'consumer',
+            broker: 'nats',
+            confidence: 0.8,
+            symbolName: 'nc.subscribe',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#match? @obj "^(nc|js)$")
+          property: (property_identifier) @prop (#match? @prop "^[Ss]ubscribe$"))
+        arguments: (arguments . [(string) (template_string)] @value))
+    `,
+    },
+    {
+        meta: {
+            role: 'provider',
+            broker: 'nats',
+            confidence: 0.8,
+            symbolName: 'nc.publish',
+        },
+        query: `
+      (call_expression
+        function: (member_expression
+          object: (identifier) @obj (#match? @obj "^(nc|js)$")
+          property: (property_identifier) @prop (#match? @prop "^[Pp]ublish$"))
+        arguments: (arguments . [(string) (template_string)] @value))
+    `,
+    },
+];
+const JAVASCRIPT_TOPIC_SPEC = {
+    name: 'javascript-topic',
+    language: JavaScript,
+    patterns: NODE_TOPIC_PATTERNS,
+};
+const TYPESCRIPT_TOPIC_SPEC = {
+    name: 'typescript-topic',
+    language: TypeScript.typescript,
+    patterns: NODE_TOPIC_PATTERNS,
+};
+const TSX_TOPIC_SPEC = {
+    name: 'tsx-topic',
+    language: TypeScript.tsx,
+    patterns: NODE_TOPIC_PATTERNS,
+};
+export const JAVASCRIPT_TOPIC_PROVIDER = compilePatterns(JAVASCRIPT_TOPIC_SPEC);
+export const TYPESCRIPT_TOPIC_PROVIDER = compilePatterns(TYPESCRIPT_TOPIC_SPEC);
+export const TSX_TOPIC_PROVIDER = compilePatterns(TSX_TOPIC_SPEC);

package/dist/core/group/extractors/topic-patterns/python.d.ts

@@ -0,0 +1,2 @@
+import type { TopicMeta } from './types.js';
+export declare const PYTHON_TOPIC_PROVIDER: import("../tree-sitter-scanner.js").CompiledPatterns<TopicMeta>;

package/dist/core/group/extractors/topic-patterns/python.js

@@ -0,0 +1,116 @@
+import Python from 'tree-sitter-python';
+import { compilePatterns } from '../tree-sitter-scanner.js';
+/**
+ * Python topic extraction patterns.
+ *
+ * Detects kafka-python, pika (RabbitMQ), and nats-py producer/consumer APIs:
+ *   - `KafkaConsumer('topic', ...)`
+ *   - `producer.send('topic', ...)` / `producer.produce('topic', ...)`
+ *   - `channel.basic_consume(queue='xxx', ...)`
+ *   - `channel.basic_publish(exchange='xxx', ...)`
+ *   - `await nc.subscribe('topic')`
+ *   - `await nc.publish('topic', ...)`
+ *
+ * Every query MUST bind `@value` to the topic literal node.
+ */
+const PYTHON_TOPIC_SPEC = {
+    name: 'python-topic',
+    language: Python,
+    patterns: [
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'kafka',
+                confidence: 0.7,
+                symbolName: 'KafkaConsumer',
+            },
+            query: `
+        (call
+          function: (identifier) @func (#eq? @func "KafkaConsumer")
+          arguments: (argument_list . (string) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'kafka',
+                confidence: 0.7,
+                symbolName: 'producer.send',
+            },
+            query: `
+        (call
+          function: (attribute
+            object: (identifier) @obj (#eq? @obj "producer")
+            attribute: (identifier) @method (#match? @method "^(send|produce)$"))
+          arguments: (argument_list . (string) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'rabbitmq',
+                confidence: 0.7,
+                symbolName: 'basic_consume',
+            },
+            query: `
+        (call
+          function: (attribute
+            object: (identifier) @obj (#eq? @obj "channel")
+            attribute: (identifier) @method (#eq? @method "basic_consume"))
+          arguments: (argument_list
+            (keyword_argument
+              name: (identifier) @kw (#eq? @kw "queue")
+              value: (string) @value)))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'rabbitmq',
+                confidence: 0.7,
+                symbolName: 'basic_publish',
+            },
+            query: `
+        (call
+          function: (attribute
+            object: (identifier) @obj (#eq? @obj "channel")
+            attribute: (identifier) @method (#eq? @method "basic_publish"))
+          arguments: (argument_list
+            (keyword_argument
+              name: (identifier) @kw (#eq? @kw "exchange")
+              value: (string) @value)))
+      `,
+        },
+        {
+            meta: {
+                role: 'consumer',
+                broker: 'nats',
+                confidence: 0.75,
+                symbolName: 'nc.subscribe',
+            },
+            query: `
+        (call
+          function: (attribute
+            object: (identifier) @obj (#eq? @obj "nc")
+            attribute: (identifier) @method (#eq? @method "subscribe"))
+          arguments: (argument_list . (string) @value))
+      `,
+        },
+        {
+            meta: {
+                role: 'provider',
+                broker: 'nats',
+                confidence: 0.75,
+                symbolName: 'nc.publish',
+            },
+            query: `
+        (call
+          function: (attribute
+            object: (identifier) @obj (#eq? @obj "nc")
+            attribute: (identifier) @method (#eq? @method "publish"))
+          arguments: (argument_list . (string) @value))
+      `,
+        },
+    ],
+};
+export const PYTHON_TOPIC_PROVIDER = compilePatterns(PYTHON_TOPIC_SPEC);

package/dist/core/group/extractors/topic-patterns/types.d.ts

@@ -0,0 +1,25 @@
+/**
+ * Shared types for the topic-extractor language plugins.
+ *
+ * Each plugin lives in its own file (java.ts, go.ts, ...) and owns the
+ * tree-sitter grammar import + query sources. The top-level
+ * `topic-extractor.ts` orchestrator only knows about this type module and
+ * the plugin registry (`./index.ts`). It MUST NOT import any grammar or
+ * query text directly — that's the whole point of the split.
+ */
+export type Broker = 'kafka' | 'rabbitmq' | 'nats';
+/**
+ * Per-pattern payload every topic plugin attaches to its query. Whatever
+ * the pattern matches, the orchestrator receives this object verbatim
+ * and uses it to build an `ExtractedContract`.
+ *
+ * Plugins produce one `TopicMeta` per pattern (not per match) because a
+ * single query uniquely identifies its broker/role/confidence triple.
+ */
+export interface TopicMeta {
+    role: 'provider' | 'consumer';
+    broker: Broker;
+    confidence: number;
+    /** Short human-readable label of the API being detected. */
+    symbolName: string;
+}

package/dist/core/group/extractors/topic-patterns/types.js

@@ -0,0 +1,10 @@
+/**
+ * Shared types for the topic-extractor language plugins.
+ *
+ * Each plugin lives in its own file (java.ts, go.ts, ...) and owns the
+ * tree-sitter grammar import + query sources. The top-level
+ * `topic-extractor.ts` orchestrator only knows about this type module and
+ * the plugin registry (`./index.ts`). It MUST NOT import any grammar or
+ * query text directly — that's the whole point of the split.
+ */
+export {};