Merge branch 'main' into fix/utf8-docstring-truncation-1017

Author: harshitaajoshi

Makefile.cbm

@@ -135,6 +135,8 @@ EXTRACTION_SRCS = \
     $(CBM_DIR)/extract_k8s.c \
     $(CBM_DIR)/helpers.c \
     $(CBM_DIR)/lang_specs.c \
+    $(CBM_DIR)/macro_table.c \
+    $(CBM_DIR)/iris_export_xml.c \
     $(CBM_DIR)/service_patterns.c
 
 # LSP resolvers (compiled as one unit via lsp_all.c)

THIRD_PARTY.md

@@ -48,6 +48,15 @@ License summary:
   original upstream authors' licenses — see the manifest for per-grammar
   provenance.
 
+### tree-sitter-objectscript (UDL + routine)
+
+- **Project:** [intersystems/tree-sitter-objectscript](https://github.com/intersystems/tree-sitter-objectscript)
+- **License:** MIT
+- **Copyright:** (c) 2025 InterSystems Corporation
+- **Vendored at:** `internal/cbm/vendored/grammars/objectscript_udl/`, `internal/cbm/vendored/grammars/objectscript_routine/`
+- **Pinned commit:** `a7ffcdf`
+- **Notes:** InterSystems-maintained grammar for the ObjectScript language (InterSystems IRIS / Caché). Vendor-maintained; not in nvim-treesitter or Helix registries. Each `scanner.c`'s upstream `#include "../../common/scanner.h"` is repointed to a per-directory `objectscript_common.h` (verbatim copy of upstream `common/scanner.h`).
+
 ## Vendored C/C++ Libraries
 
 | Library | Path | License | Project |

internal/cbm/cbm.c

@@ -721,11 +721,6 @@ static bool cbm_source_nesting_exceeds(const char *source, int source_len, int c
     return false;
 }
 
-static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
-                                            CBMLanguage language, const char *project,
-                                            const char *rel_path, int64_t timeout_micros,
-                                            const char **extra_defines, const char **include_paths);
-
 /* Best-effort parse-coverage collection (#963). Walks only the has_error paths
  * of the tree and records the 1-based line ranges of the TOP-MOST ERROR/MISSING
  * nodes (does not descend into an error subtree — one range per failed region).
@@ -886,17 +881,17 @@ static const char *cbm_error_ranges_str(CBMArena *a, const cbm_error_regions_t *
 CBMFileResult *cbm_extract_file(const char *source, int source_len, CBMLanguage language,
                                 const char *project, const char *rel_path, int64_t timeout_micros,
                                 const char **extra_defines, const char **include_paths) {
-    CBMFileResult *r = cbm_extract_file_impl(source, source_len, language, project, rel_path,
-                                             timeout_micros, extra_defines, include_paths);
-    cbm_index_mark_done(rel_path);
+    CBMFileResult *r =
+        cbm_extract_file_ex(source, source_len, language, project, rel_path, timeout_micros,
+                            extra_defines, include_paths, NULL, NULL);
     return r;
 }
 
-static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
-                                            CBMLanguage language, const char *project,
-                                            const char *rel_path, int64_t timeout_micros,
-                                            const char **extra_defines,
-                                            const char **include_paths) {
+CBMFileResult *cbm_extract_file_ex(const char *source, int source_len, CBMLanguage language,
+                                   const char *project, const char *rel_path,
+                                   int64_t timeout_micros, const char **extra_defines,
+                                   const char **include_paths, const CBMMacroTable *macro_table,
+                                   const CBMReturnTypeTable *return_type_table) {
     // Allocate result on heap (arena inside for all string data)
     enum { SINGLE = 1 };
     CBMFileResult *result = (CBMFileResult *)calloc(SINGLE, sizeof(CBMFileResult));
@@ -926,6 +921,7 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
     if (!spec) {
         result->has_error = true;
         result->error_msg = cbm_arena_strdup(a, "unsupported language");
+        cbm_index_mark_done(rel_path);
         return result;
     }
 
@@ -934,6 +930,7 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
     if (!ts_lang) {
         result->has_error = true;
         result->error_msg = cbm_arena_strdup(a, "no tree-sitter grammar");
+        cbm_index_mark_done(rel_path);
         return result;
     }
 
@@ -953,6 +950,7 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
     if (!parser) {
         result->has_error = true;
         result->error_msg = cbm_arena_strdup(a, "parser alloc failed");
+        cbm_index_mark_done(rel_path);
         return result;
     }
 
@@ -985,6 +983,7 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
         result->has_error = true;
         result->error_msg =
             cbm_arena_strdup(a, timeout_micros > 0 ? "parse timeout" : "parse failed");
+        cbm_index_mark_done(rel_path);
         return result;
     }
 
@@ -1009,6 +1008,8 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
         .rel_path = rel_path,
         .module_qn = result->module_qn,
         .root = root,
+        .macro_table = macro_table,
+        .return_type_table = return_type_table,
     };
 
     // Run extractors: defs + imports use separate walks (unique recursion patterns),
@@ -1318,6 +1319,7 @@ static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
     // Retain tree for cross-file LSP reuse (caller frees via cbm_free_tree)
     result->cached_tree = tree;
     result->cached_lang = language;
+    cbm_index_mark_done(rel_path);
     return result;
 }
 

internal/cbm/cbm.h

@@ -164,13 +164,16 @@ typedef enum {
     CBM_LANG_APEX,
     CBM_LANG_SOQL,
     CBM_LANG_SOSL,
-    CBM_LANG_KUSTOMIZE, // kustomization.yaml — Kubernetes overlay tool
-    CBM_LANG_K8S,       // Generic Kubernetes manifest (apiVersion: detected)
-    CBM_LANG_PINE,      // Pine Script (TradingView indicator / strategy language)
-    CBM_LANG_QML,       // Qt QML (Qt Modeling Language — declarative UI + embedded JS)
-    CBM_LANG_CFSCRIPT,  // CFML script dialect (.cfc components — Lucee/ColdFusion)
-    CBM_LANG_CFML,      // CFML tag dialect (.cfm templates — Lucee/ColdFusion)
-    CBM_LANG_MOJO,      // Mojo
+    CBM_LANG_KUSTOMIZE,            // kustomization.yaml — Kubernetes overlay tool
+    CBM_LANG_K8S,                  // Generic Kubernetes manifest (apiVersion: detected)
+    CBM_LANG_PINE,                 // Pine Script (TradingView indicator / strategy language)
+    CBM_LANG_QML,                  // Qt QML (Qt Modeling Language — declarative UI + embedded JS)
+    CBM_LANG_CFSCRIPT,             // CFML script dialect (.cfc components — Lucee/ColdFusion)
+    CBM_LANG_CFML,                 // CFML tag dialect (.cfm templates — Lucee/ColdFusion)
+    CBM_LANG_MOJO,                 // Mojo
+    CBM_LANG_OBJECTSCRIPT_UDL,     // InterSystems ObjectScript UDL (.cls class files)
+    CBM_LANG_OBJECTSCRIPT_ROUTINE, // InterSystems ObjectScript routine (.mac/.int/.rtn/.inc)
+    CBM_LANG_OBJECTSCRIPT_EXPORT,  // InterSystems Studio Export XML (<Export generator="Cache">)
     CBM_LANG_COUNT
 } CBMLanguage;
 
@@ -499,6 +502,24 @@ typedef struct {
     int count;
 } CBMStringConstantMap;
 
+// Forward declaration: ObjectScript macro table (defined in macro_table.h).
+typedef struct CBMMacroTable CBMMacroTable;
+
+// Method-return-type table for ObjectScript variable type inference. Populated
+// from definition nodes (method QN -> declared return type) so a later
+// `Set x = obj.Method()` can resolve x's class.
+#define CBM_RETURN_TYPE_TABLE_CAP 2048
+
+typedef struct {
+    const char *method_qn;
+    const char *return_type;
+} CBMReturnTypeEntry;
+
+typedef struct {
+    CBMReturnTypeEntry entries[CBM_RETURN_TYPE_TABLE_CAP];
+    int count;
+} CBMReturnTypeTable;
+
 typedef struct {
     CBMArena *arena;
     CBMFileResult *result;
@@ -509,9 +530,11 @@ typedef struct {
     const char *rel_path;
     const char *module_qn;
     TSNode root;
-    EFCache ef_cache;                      // enclosing function cache
-    const char *enclosing_class_qn;        // for nested class QN computation
-    CBMStringConstantMap string_constants; // module-level NAME = "value" pairs
+    EFCache ef_cache;                            // enclosing function cache
+    const char *enclosing_class_qn;              // for nested class QN computation
+    CBMStringConstantMap string_constants;       // module-level NAME = "value" pairs
+    const CBMMacroTable *macro_table;            // ObjectScript $$$macro table (NULL if none)
+    const CBMReturnTypeTable *return_type_table; // ObjectScript method return types (NULL if none)
 } CBMExtractCtx;
 
 // --- Public API ---
@@ -561,6 +584,18 @@ CBMFileResult *cbm_extract_file(const char *source, int source_len, CBMLanguage
                                 const char **include_paths  // NULL-terminated, or NULL
 );
 
+// Pipeline-internal variant of cbm_extract_file() carrying ObjectScript
+// per-project tables (macro table + method-return-type table). The public
+// cbm_extract_file() is a thin wrapper that passes NULL, NULL for both.
+CBMFileResult *cbm_extract_file_ex(
+    const char *source, int source_len, CBMLanguage language, const char *project,
+    const char *rel_path, int64_t timeout_micros,
+    const char **extra_defines,                 // NULL-terminated, or NULL
+    const char **include_paths,                 // NULL-terminated, or NULL
+    const CBMMacroTable *macro_table,           // ObjectScript macros, or NULL
+    const CBMReturnTypeTable *return_type_table // OS return types, or NULL
+);
+
 // Free all memory associated with a result.
 void cbm_free_result(CBMFileResult *result);