Add C emitters with local rule and output state

Author: pablogsal

Tools/peg_generator/pegen/c_generator_file.py

@@ -0,0 +1,82 @@
+"""Emit a complete C parser from an immutable plan and local output state."""
+
+from collections.abc import Iterator
+from contextlib import contextmanager
+from typing import IO
+
+from pegen.c_generator_model import CParser
+from pegen.c_generator_rules import CRuleEmitter
+
+
+class CParserEmitter:
+    def __init__(self, parser: CParser, file: IO[str] | None):
+        self._parser = parser
+        self._file = file
+        self._level = 0
+
+    def emit(self) -> None:
+        self._emit_headers()
+        self._emit_keywords()
+        self._emit_declarations()
+        self._emit_rules()
+        if self._parser.trailer is not None:
+            self.print(self._parser.trailer)
+
+    def _emit_headers(self) -> None:
+        self.print(f"// @generated by pegen from {self._parser.source_name}")
+        for header in self._parser.headers:
+            self.print(header)
+
+    def _emit_keywords(self) -> None:
+        groups = self._parser.keyword_groups
+        self.print(f"static const int n_keyword_lists = {len(groups)};")
+        self.print("static KeywordToken *reserved_keywords[] = {")
+        with self.indent():
+            for group in groups or ((),):
+                if not group:
+                    self.print("(KeywordToken[]) {{NULL, -1}},")
+                else:
+                    self.print("(KeywordToken[]) {")
+                    with self.indent():
+                        for keyword, token_type in group:
+                            self.print(f'{{"{keyword}", {token_type}}},')
+                        self.print("{NULL, -1},")
+                    self.print("},")
+        self.print("};")
+        self.print("static char *soft_keywords[] = {")
+        with self.indent():
+            for keyword in self._parser.soft_keywords:
+                self.print(f'"{keyword}",')
+            self.print("NULL,")
+        self.print("};")
+
+    def _emit_declarations(self) -> None:
+        for rule_id, rule in enumerate(self._parser.rules, 1000):
+            comment = "  // Left-recursive" if rule.left_recursive else ""
+            self.print(f"#define {rule.signature.name}_type {rule_id}{comment}")
+        self.print()
+        for rule in self._parser.rules:
+            self.print(rule.signature.declaration())
+        self.print()
+
+    def _emit_rules(self) -> None:
+        for rule in self._parser.rules:
+            self.print()
+            if rule.left_recursive:
+                self.print("// Left-recursive")
+            CRuleEmitter(self, rule, debug=self._parser.debug).emit()
+
+    def print(self, *args: object) -> None:
+        if not args:
+            print(file=self._file)
+        else:
+            print("    " * self._level, end="", file=self._file)
+            print(*args, file=self._file)
+
+    @contextmanager
+    def indent(self) -> Iterator[None]:
+        self._level += 1
+        try:
+            yield
+        finally:
+            self._level -= 1