From acce00228b842af35df5af8c97398765a386ab1e Mon Sep 17 00:00:00 2001
From: Rui Ueyama <ruiu@cs.stanford.edu>
Date: Sun, 29 Mar 2020 15:47:50 +0900
Subject: [PATCH] Do not expand a token more than once for the same objlike
 macro

---
 chibicc.h    | 24 ++++++++++--------
 preprocess.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 test/macro.c | 12 +++++++++
 3 files changed, 96 insertions(+), 12 deletions(-)

diff --git a/chibicc.h b/chibicc.h
index 51aefe6..d3a0cd2 100644
--- a/chibicc.h
+++ b/chibicc.h
@@ -23,6 +23,7 @@ typedef struct Type Type;
 typedef struct Node Node;
 typedef struct Member Member;
 typedef struct Relocation Relocation;
+typedef struct Hideset Hideset;
 
 //
 // strings.c
@@ -60,18 +61,19 @@ typedef struct {
 // Token type
 typedef struct Token Token;
 struct Token {
-  TokenKind kind; // Token kind
-  Token *next;    // Next token
-  int64_t val;    // If kind is TK_NUM, its value
-  double fval;    // If kind is TK_NUM, its value
-  char *loc;      // Token location
-  int len;        // Token length
-  Type *ty;       // Used if TK_NUM or TK_STR
-  char *str;      // String literal contents including terminating '\0'
+  TokenKind kind;   // Token kind
+  Token *next;      // Next token
+  int64_t val;      // If kind is TK_NUM, its value
+  double fval;      // If kind is TK_NUM, its value
+  char *loc;        // Token location
+  int len;          // Token length
+  Type *ty;         // Used if TK_NUM or TK_STR
+  char *str;        // String literal contents including terminating '\0'
 
-  File *file;     // Source location
-  int line_no;    // Line number
-  bool at_bol;    // True if this token is at beginning of line
+  File *file;       // Source location
+  int line_no;      // Line number
+  bool at_bol;      // True if this token is at beginning of line
+  Hideset *hideset; // For macro expansion
 };
 
 void error(char *fmt, ...);
diff --git a/preprocess.c b/preprocess.c
index e67f324..e96d20d 100644
--- a/preprocess.c
+++ b/preprocess.c
@@ -1,3 +1,26 @@
+// This file implements the C preprocessor.
+//
+// The preprocessor takes a list of tokens as an input and returns a
+// new list of tokens as an output.
+//
+// The preprocessing language is designed in such a way that that's
+// guaranteed to stop even if there is a recursive macro.
+// Informally speaking, a macro is applied only once for each token.
+// That is, if a macro token T appears in a result of direct or
+// indirect macro expansion of T, T won't be expanded any further.
+// For example, if T is defined as U, and U is defined as T, then
+// token T is expanded to U and then to T and the macro expansion
+// stops at that point.
+//
+// To achieve the above behavior, we attach for each token a set of
+// macro names from which the token is expanded. The set is called
+// "hideset". Hideset is initially empty, and every time we expand a
+// macro, the macro name is added to the resulting tokens' hidesets.
+//
+// The above macro expansion algorithm is explained in this document,
+// which is used as a basis for the standard's wording:
+// https://github.com/rui314/chibicc/wiki/cpp.algo.pdf
+
 #include "chibicc.h"
 
 typedef struct Macro Macro;
@@ -17,6 +40,12 @@ struct CondIncl {
   bool included;
 };
 
+typedef struct Hideset Hideset;
+struct Hideset {
+  Hideset *next;
+  char *name;
+};
+
 static Macro *macros;
 static CondIncl *cond_incl;
 
@@ -51,6 +80,41 @@ static Token *new_eof(Token *tok) {
   return t;
 }
 
+static Hideset *new_hideset(char *name) {
+  Hideset *hs = calloc(1, sizeof(Hideset));
+  hs->name = name;
+  return hs;
+}
+
+static Hideset *hideset_union(Hideset *hs1, Hideset *hs2) {
+  Hideset head = {};
+  Hideset *cur = &head;
+
+  for (; hs1; hs1 = hs1->next)
+    cur = cur->next = new_hideset(hs1->name);
+  cur->next = hs2;
+  return head.next;
+}
+
+static bool hideset_contains(Hideset *hs, char *s, int len) {
+  for (; hs; hs = hs->next)
+    if (strlen(hs->name) == len && !strncmp(hs->name, s, len))
+      return true;
+  return false;
+}
+
+static Token *add_hideset(Token *tok, Hideset *hs) {
+  Token head = {};
+  Token *cur = &head;
+
+  for (; tok; tok = tok->next) {
+    Token *t = copy_token(tok);
+    t->hideset = hideset_union(t->hideset, hs);
+    cur = cur->next = t;
+  }
+  return head.next;
+}
+
 // Append tok2 to the end of tok1.
 static Token *append(Token *tok1, Token *tok2) {
   if (tok1->kind == TK_EOF)
@@ -159,10 +223,16 @@ static Macro *add_macro(char *name, Token *body) {
 // If tok is a macro, expand it and return true.
 // Otherwise, do nothing and return false.
 static bool expand_macro(Token **rest, Token *tok) {
+  if (hideset_contains(tok->hideset, tok->loc, tok->len))
+    return false;
+
   Macro *m = find_macro(tok);
   if (!m)
     return false;
-  *rest = append(m->body, tok->next);
+
+  Hideset *hs = hideset_union(tok->hideset, new_hideset(m->name));
+  Token *body = add_hideset(m->body, hs);
+  *rest = append(body, tok->next);
   return true;
 }
 
diff --git a/test/macro.c b/test/macro.c
index 61447f6..787cbf3 100644
--- a/test/macro.c
+++ b/test/macro.c
@@ -144,6 +144,18 @@ int main() {
 #endif
   assert(5, m, "m");
 
+  int M2 = 6;
+#define M2 M2 + 3
+  assert(9, M2, "M2");
+
+#define M3 M2 + 3
+  assert(12, M3, "M3");
+
+  int M4 = 3;
+#define M4 M5 * 5
+#define M5 M4 + 2
+  assert(13, M4, "M4");
+
   printf("OK\n");
   return 0;
 }