feat(docs): doc-comment links for eight more languages, diagrams and OpenAPI operations in the graph

Makefile.cbm

@@ -386,6 +386,16 @@ EXTRACTION_SRCS = \
     $(CBM_DIR)/pdf/pdf_text.c \
     $(CBM_DIR)/pdf/pdf_tables.c \
     $(CBM_DIR)/pdf/pdf_unicode.c \
+    $(CBM_DIR)/doclink_go.c \
+    $(CBM_DIR)/doclink_jvm.c \
+    $(CBM_DIR)/doclink_rs.c \
+    $(CBM_DIR)/doclink_perl.c \
+    $(CBM_DIR)/doclink_ts.c \
+    $(CBM_DIR)/doclink_php.c \
+    $(CBM_DIR)/doclink_c.c \
+    $(CBM_DIR)/diagram.c \
+    $(CBM_DIR)/route_path.c \
+    $(CBM_DIR)/openapi.c \
     $(CBM_DIR)/sql_values.c \
     $(CBM_DIR)/helpers.c \
     $(CBM_DIR)/cpp_branch_views.c \
@@ -512,6 +522,14 @@ PIPELINE_SRCS = \
     src/pipeline/doc_links_pdf.c \
     src/pipeline/doc_links_rst.c \
     src/pipeline/doc_links_adoc.c \
+    src/pipeline/doc_links_go.c \
+    src/pipeline/doc_links_jvm.c \
+    src/pipeline/doc_links_rs.c \
+    src/pipeline/doc_links_perl.c \
+    src/pipeline/doc_links_ts.c \
+    src/pipeline/doc_links_php.c \
+    src/pipeline/doc_links_c.c \
+    src/pipeline/pass_diagrams.c \
     src/pipeline/doc_links_msbuild.c \
     src/pipeline/pass_route_nodes.c \
     src/pipeline/pass_enrichment.c \
@@ -774,7 +792,7 @@ TEST_DISCOVER_SRCS = \
 
 TEST_GRAPH_BUFFER_SRCS = tests/test_graph_buffer.c
 
-TEST_PIPELINE_SRCS = tests/test_registry.c tests/test_pipeline.c tests/test_pipeline_conventions.c tests/test_pipeline_frozen.c tests/test_importance.c tests/test_cross_repo.c tests/test_fqn.c tests/test_route_canon.c tests/test_path_alias.c tests/test_configlink.c tests/test_doclinks.c tests/test_doc_mentions.c tests/test_doc_links_md.c tests/test_doc_links_pdf.c tests/test_doc_links_rst.c tests/test_doc_links_adoc.c tests/test_infrascan.c tests/test_worker_pool.c tests/test_parallel.c tests/test_index_resilience.c tests/test_index_format.c tests/test_call_reference_contract.c tests/repro/repro_call_scope_usages.c tests/repro/repro_call_argument_usages.c tests/repro/repro_reference_precision.c tests/repro/repro_lexical_binding_precision.c tests/repro/repro_call_argument_matrix_a.c tests/repro/repro_call_argument_matrix_b.c tests/repro/repro_call_node_behaviors.c tests/repro/repro_language_registry.c tests/repro/repro_call_node_manifest.c tests/repro/repro_lsp_ordered_signatures.c tests/repro/repro_lsp_ordered_local.c tests/repro/repro_ts_overload_return_chains.c tests/repro/repro_harness_cleanup.c tests/repro/repro_runner_filter.c
+TEST_PIPELINE_SRCS = tests/test_registry.c tests/test_pipeline.c tests/test_pipeline_conventions.c tests/test_pipeline_frozen.c tests/test_importance.c tests/test_cross_repo.c tests/test_fqn.c tests/test_route_canon.c tests/test_path_alias.c tests/test_configlink.c tests/test_doclinks.c tests/test_doc_mentions.c tests/test_doc_links_md.c tests/test_doc_links_pdf.c tests/test_doc_links_rst.c tests/test_doc_links_adoc.c tests/test_doc_mentions_go.c tests/test_doc_mentions_jvm.c tests/test_doc_mentions_rs.c tests/test_doc_mentions_perl.c tests/test_doc_mentions_ts.c tests/test_doc_mentions_php.c tests/test_doc_mentions_c.c tests/test_diagrams.c tests/test_openapi.c tests/test_infrascan.c tests/test_worker_pool.c tests/test_parallel.c tests/test_index_resilience.c tests/test_index_format.c tests/test_call_reference_contract.c tests/repro/repro_call_scope_usages.c tests/repro/repro_call_argument_usages.c tests/repro/repro_reference_precision.c tests/repro/repro_lexical_binding_precision.c tests/repro/repro_call_argument_matrix_a.c tests/repro/repro_call_argument_matrix_b.c tests/repro/repro_call_node_behaviors.c tests/repro/repro_language_registry.c tests/repro/repro_call_node_manifest.c tests/repro/repro_lsp_ordered_signatures.c tests/repro/repro_lsp_ordered_local.c tests/repro/repro_ts_overload_return_chains.c tests/repro/repro_harness_cleanup.c tests/repro/repro_runner_filter.c
 
 TEST_WATCHER_SRCS = tests/test_watcher.c
 

internal/cbm/cbm.c

@@ -277,6 +277,11 @@ void cbm_channels_push(CBMChannelArray *arr, CBMArena *a, CBMChannel ch) {
     arr->items[arr->count++] = ch;
 }
 
+void cbm_diagram_arrows_push(CBMDiagramArrowArray *arr, CBMArena *a, CBMDiagramArrow da) {
+    GROW_ARRAY(arr, a);
+    arr->items[arr->count++] = da;
+}
+
 // --- String input reader (for parse_with_options) ---
 
 typedef struct {
@@ -2837,6 +2842,26 @@ static CBMFileResult *extract_file_ex_body(const char *source, int source_len, C
             .module_qn = result->module_qn,
         };
         cbm_adoc_extract_document(&adoc_ctx);
+        cbm_extract_diagrams(&adoc_ctx); /* after the Sections they hang under */
+        cbm_index_mark_done(rel_path);
+        return result;
+    }
+    /* Diagram files have no grammar either: each format is read from the text
+     * (diagram.c). */
+    if (language == CBM_LANG_DIAGRAM) {
+        result->module_qn = cbm_fqn_module_source_lang(a, project, rel_path, language);
+        CBMExtractCtx diagram_ctx = {
+            .arena = a,
+            .scratch = scratch,
+            .result = result,
+            .source = source,
+            .source_len = source_len,
+            .language = language,
+            .project = project,
+            .rel_path = rel_path,
+            .module_qn = result->module_qn,
+        };
+        cbm_extract_diagram_file(&diagram_ctx);
         cbm_index_mark_done(rel_path);
         return result;
     }
@@ -3021,6 +3046,12 @@ static CBMFileResult *extract_file_ex_body(const char *source, int source_len, C
     // Channel detection (Socket.IO / EventEmitter) — JS/TS only.
     cbm_extract_channels(&ctx);
 
+    // Diagrams: blocks of documents and diagram files (self-gated by language).
+    cbm_extract_diagrams(&ctx);
+
+    // OpenAPI operations as Routes (self-gated: API description documents).
+    cbm_extract_openapi(&ctx);
+
     // K8s / Kustomize semantic pass (additional structured extraction for YAML-based infra files).
     if (ctx.language == CBM_LANG_KUSTOMIZE || ctx.language == CBM_LANG_K8S) {
         cbm_extract_k8s(&ctx);

internal/cbm/cbm.h

@@ -211,6 +211,10 @@ typedef enum {
     CBM_LANG_CHIALISP, // Chialisp (.clsp/.clib/.clinc — Chia smart-coin s-expression language)
     CBM_LANG_PDF,      // PDF documents: the text layer, read without a grammar (doc_pdf.c)
     CBM_LANG_ASCIIDOC, // AsciiDoc documents, read without a grammar (doc_adoc.c)
+    CBM_LANG_OPENAPI,  // openapi.json / swagger.json: the JSON grammar, no node per key; their
+                       // operations are Routes (openapi.c)
+    CBM_LANG_DIAGRAM,  // diagram files (PlantUML, DOT, D2, draw.io, Excalidraw), read
+                       // without a grammar (diagram.c)
     CBM_LANG_COUNT
 } CBMLanguage;
 
@@ -612,6 +616,23 @@ typedef struct {
     int cap;
 } CBMChannelArray;
 
+/* One arrow of a diagram (diagram.c): from one DiagramElement definition of
+ * the file to another, written as a DIAGRAM_ARROW edge. */
+typedef struct {
+    const char *from_qn;
+    const char *to_qn;
+    const char *label; /* the arrow's text, NULL for none */
+    const char *style; /* what the arrow means as its format writes it: "flow",
+                        * "message", "inherits", "composition", ... */
+    uint32_t line;
+} CBMDiagramArrow;
+
+typedef struct {
+    CBMDiagramArrow *items;
+    int count;
+    int cap;
+} CBMDiagramArrowArray;
+
 typedef struct {
     CBMFieldType *items;
     int count;
@@ -661,6 +682,7 @@ typedef struct CBMFileResult {
     CBMStringRefArray string_refs;       // URL/config string literals from AST
     CBMInfraBindingArray infra_bindings; // topic→URL pairs from IaC configs
     CBMChannelArray channels;            // Socket.IO / EventEmitter pub/sub participation
+    CBMDiagramArrowArray diagram_arrows; // arrows between the file's DiagramElement defs
     CBMFieldTypeArray field_types;       // Python: annotated instance fields (#1277)
 
     const char *module_qn;      // module qualified name
@@ -1122,6 +1144,7 @@ void cbm_infrabinding_push(CBMInfraBindingArray *arr, CBMArena *a, CBMInfraBindi
 void cbm_impltrait_push(CBMImplTraitArray *arr, CBMArena *a, CBMImplTrait it);
 void cbm_resolvedcall_push(CBMResolvedCallArray *arr, CBMArena *a, CBMResolvedCall rc);
 void cbm_channels_push(CBMChannelArray *arr, CBMArena *a, CBMChannel ch);
+void cbm_diagram_arrows_push(CBMDiagramArrowArray *arr, CBMArena *a, CBMDiagramArrow da);
 
 // --- Sub-extractor entry points ---
 
@@ -1140,6 +1163,31 @@ void cbm_extract_type_refs(CBMExtractCtx *ctx);
 void cbm_extract_env_accesses(CBMExtractCtx *ctx);
 void cbm_extract_type_assigns(CBMExtractCtx *ctx);
 void cbm_extract_channels(CBMExtractCtx *ctx);
+/* Diagrams (diagram.c): a Diagram definition per diagram -- a Markdown, reST
+ * or AsciiDoc block, or a diagram file -- with a DiagramElement definition per
+ * element and the arrows between them. */
+void cbm_extract_diagrams(CBMExtractCtx *ctx);
+/* Is a Markdown block a diagram fence, and the labels its parser reads from
+ * it (space-joined; NULL for none): a Section's text keeps those labels in
+ * place of the fence (extract_markdown_section_body). */
+bool cbm_diagram_fence_is_diagram(const char *source, TSNode block);
+const char *cbm_diagram_fence_labels(CBMExtractCtx *ctx, TSNode block);
+/* A diagram file (CBM_LANG_DIAGRAM): its format comes from its extension. */
+void cbm_extract_diagram_file(CBMExtractCtx *ctx);
+
+/* OpenAPI / Swagger documents (openapi.c): a Route definition per operation and
+ * a doc link per operationId. Self-gated: openapi.json / swagger.json, and YAML
+ * or JSON files whose root says `openapi` or `swagger`. */
+void cbm_extract_openapi(CBMExtractCtx *ctx);
+
+/* Canonicalize route-path parameter placeholders (":id", "{id}", "<id>",
+ * "${...}") to a single "{}" token so that client call sites, server handlers
+ * and OpenAPI operations rendezvous on the same Route QN regardless of
+ * framework syntax. Parameter names are intentionally discarded ("/u/{id}" and
+ * "/u/{slug}" both canonicalize to "/u/{}"). The result never exceeds the
+ * input length, so out_sz >= strlen(in) + 1 always suffices. Returns out.
+ * (route_path.c) */
+const char *cbm_route_canon_path(const char *in, char *out, size_t out_sz);
 
 // Single-pass unified extraction (replaces the 7 calls above except defs+imports).
 void cbm_extract_unified(CBMExtractCtx *ctx);