mirror of
https://github.com/DeusData/codebase-memory-mcp.git
synced 2026-11-04 10:48:20 +00:00
Martin Vogel
42a9320200
The test-impact engine selects tests by walking the graph, so it can only be as right as the graph. Three gaps made it wrong: One identity for a definition's mutually exclusive variants - A definition written once per #if/#else branch, per #[cfg], per platform file (foo_linux.c / foo_win.c, platform directories) or per Go build tag is ONE node. The graph buffer keeps every variant's span in a `variants` node property (definition labels only), so a change in any variant maps to the definition. - Extraction now sees definitions inside conditional blocks where it skipped them: C++/C#/ObjC class members under #if (one cursor walk, conditional block types per language in lang_specs), Elixir defs under if/unless, Fortran .F90/.F95/.F03/.F08, Rust #[cfg] twins (no more `name#cfg(...)` QNs that lost every call), C platform files and directories (non-static file-scope functions). - Haskell: the vendored scanner reads only an #if group's first branch. The grammar stays upstream; every further branch is parsed as its own same-length view (cpp_branch_views.c) and adds what the raw parse missed. haskell/bytestring: no new partial parses, +27 functions, IMPORTS 322 -> 329, 131 definitions with variant spans. - Incremental closure repair re-parses every file of such a definition when one of them changes (variant partners through DEFINES), so a repair equals a full index. No cross-language name guesses - A name-only resolution (unique_name, suffix_match, qualified_suffix, field_type_hint, and same_module across files that only share a path stem) never binds a symbol another language defines. - Bash imports are the files a script sources: every top-level command was read as an import of its name (`set -e` imported "set", bound to a TSX method in 137 scripts here). - This repository: cross-language CALLS 5,916 -> 5,091; the remainder are C/C++ pairs, builtins and same-stem module collisions (recorded). SPAWNS edges (per language, like the HTTP client patterns) - A call that starts a program (subprocess.run, exec.Command, child_process.spawn, posix_spawn, system, Process.Start, Command::new, ... about 30 languages, through the file's own imports) gets a SPAWNS edge to a Process node named after the program (literal first word, or <dynamic>) instead of a CALLS guess. No target resolution. Both resolvers ask at the same point (parity test). The engine follows the graph - Seeds map changed lines through every variant span; a test written once per #if branch is one test; when a change reaches a non-test `main`, the tests that spawn processes are reached too (the process runs main, and main reaches everything). Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
66 lines
3.1 KiB
C
66 lines
3.1 KiB
C
#ifndef CBM_LANG_SPECS_H
|
|
#define CBM_LANG_SPECS_H
|
|
|
|
#include "cbm.h"
|
|
|
|
// CBMEmbeddedLangSpec describes a sub-language embedded inside a host AST.
|
|
// Used by host grammars whose tree-sitter parser does not recurse into the
|
|
// embedded content (e.g. Svelte, Vue, Astro: script_element -> raw_text holds
|
|
// JavaScript verbatim that the host grammar leaves unparsed). The generic
|
|
// embedded-imports walker locates each script_node_type in the host AST,
|
|
// finds its content_node_type child, and re-parses that slice with the
|
|
// embedded_language's grammar so existing extractors run on the inner AST.
|
|
typedef struct {
|
|
const char *script_node_type; // e.g. "script_element"
|
|
const char *content_node_type; // e.g. "raw_text"
|
|
CBMLanguage embedded_language; // grammar used to re-parse the content slice
|
|
} CBMEmbeddedLangSpec;
|
|
|
|
// CBMLangSpec mirrors Go's lang.LanguageSpec with NULL-terminated string arrays.
|
|
typedef struct {
|
|
CBMLanguage language;
|
|
const char **function_node_types;
|
|
const char **class_node_types;
|
|
const char **field_node_types;
|
|
const char **module_node_types;
|
|
const char **call_node_types;
|
|
const char **import_node_types;
|
|
const char **import_from_types;
|
|
const char **branching_node_types;
|
|
const char **variable_node_types;
|
|
const char **assignment_node_types;
|
|
const char **throw_node_types;
|
|
const char *throws_clause_field; // NULL if none
|
|
const char **decorator_node_types;
|
|
const char **env_access_functions; // NULL-terminated (NULL if none)
|
|
const char **env_access_member_patterns; // NULL-terminated (NULL if none)
|
|
const TSLanguage *(*ts_factory)(void); // Tree-sitter grammar factory (NULL if shared)
|
|
// NULL-terminated list of embedded sub-languages (NULL if host grammar has
|
|
// no embedded content to re-parse). The terminator is an entry whose
|
|
// script_node_type is NULL.
|
|
const CBMEmbeddedLangSpec *embedded_imports;
|
|
} CBMLangSpec;
|
|
|
|
// Returns a NULL-terminated list of callee-name suffixes that indicate a
|
|
// string-dispatch call for a given language (e.g. ".classMethodValue" for
|
|
// Python/IRIS), or NULL if the language has no such dispatch pattern.
|
|
// Kept out of CBMLangSpec to avoid -Wmissing-field-initializers across 155
|
|
// language rows; the table lives in extract_calls.c next to the dispatch code.
|
|
const char **cbm_string_dispatch_suffixes(CBMLanguage lang);
|
|
|
|
// Returns a NULL-terminated list of node types that wrap conditionally
|
|
// compiled alternatives (#if/#ifdef/#else/#elif blocks) for a language, or
|
|
// NULL when the grammar has none. A definition inside one is still a member
|
|
// of its enclosing scope; its #else twin is a variant of the same definition.
|
|
// Side table for the same -Wmissing-field-initializers reason as above.
|
|
const char **cbm_conditional_block_types(CBMLanguage lang);
|
|
|
|
// Get the language spec for a given language. Returns NULL for unsupported.
|
|
const CBMLangSpec *cbm_lang_spec(CBMLanguage lang);
|
|
|
|
// Get the TSLanguage* for a given language. Returns NULL for unsupported.
|
|
// These resolve at link time to grammar symbols from Go tree-sitter modules.
|
|
const TSLanguage *cbm_ts_language(CBMLanguage lang);
|
|
|
|
#endif // CBM_LANG_SPECS_H
|