[PATCH] D82092: [analyzer] Handle `\l` symbol in string literals in exploded-graph-rewriter

[Denys Petrov via Phabricator via cfe-commits]

ASDenysPetrov updated this revision to Diff 272007.
ASDenysPetrov added a comment.

Expanded the patch for all platforms.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D82092/new/

https://reviews.llvm.org/D82092

Files:
  clang/test/Analysis/exploded-graph-rewriter/l_name_starts_with_l.cpp
  clang/utils/analyzer/exploded-graph-rewriter.py


Index: clang/utils/analyzer/exploded-graph-rewriter.py
===================================================================
--- clang/utils/analyzer/exploded-graph-rewriter.py
+++ clang/utils/analyzer/exploded-graph-rewriter.py
@@ -368,8 +368,7 @@
                 self.root_id = node_id
             # Note: when writing tests you don't need to escape everything,
             # even though in a valid dot file everything is escaped.
-            node_label = result.group(2).replace('\\l', '') \
-                                        .replace(' ', '') \
+            node_label = result.group(2).replace(' ', '') \
                                         .replace('\\"', '"') \
                                         .replace('\\{', '{') \
                                         .replace('\\}', '}') \
@@ -378,6 +377,13 @@
                                         .replace('\\<', '\\\\<') \
                                         .replace('\\>', '\\\\>') \
                                         .rstrip(',')
+            # Handle `\l` separately because a string literal can be in code
+            # like "string\\literal" with the `\l` inside.
+            # Also on Windows macros __FILE__ produces specific delimiters `\`
+            # and a directory or file may starts with the letter `l`.
+            # Find all `\l` (like `,\l`, `}\l`, `[\l`) except `\\l`,
+            # because the literal as a rule containes multiple `\` before `\l`.
+            node_label = re.sub(r'(?<!\\)\\l', '', node_label)
             logging.debug(node_label)
             json_node = json.loads(node_label)
             self.nodes[node_id].construct(node_id, json_node)
@@ -422,8 +428,8 @@
              .replace('}', '\\}') \
              .replace('\\<', '<') \
              .replace('\\>', '>') \
-             .replace('\\l', '<br />') \
              .replace('|', '\\|')
+        s = re.sub(r'(?<!\\)\\l', '<br />', s)
         if self._gray_mode:
             s = re.sub(r'<font color="[a-z0-9]*">', '', s)
             s = re.sub(r'</font>', '', s)
Index: clang/test/Analysis/exploded-graph-rewriter/l_name_starts_with_l.cpp
===================================================================
--- /dev/null
+++ clang/test/Analysis/exploded-graph-rewriter/l_name_starts_with_l.cpp
@@ -0,0 +1,26 @@
+// CAUTION: The name of this file should start with `l` for proper tests.
+// FIXME: Figure out how to use %clang_analyze_cc1 with our lit.local.cfg.
+// RUN: %clang_cc1 -analyze -triple x86_64-unknown-linux-gnu \
+// RUN:                     -analyzer-checker=core \
+// RUN:                     -analyzer-dump-egraph=%t.dot %s
+// RUN: %exploded_graph_rewriter %t.dot | FileCheck %s
+// REQUIRES: asserts
+
+void test1() {
+  // Here __FILE__ macros produces a string with `\` delimiters on Windows
+  // and the name of the file starts with `l`.
+  char text[] = __FILE__;
+}
+
+void test2() {
+  // Here `\l` is in the middle of the literal.
+  char text[] = "string\\literal";
+}
+
+void test() {
+  test1();
+  test2();
+}
+
+// This test is passed if exploded_graph_rewriter handles dot file without errors.
+// CHECK: digraph "ExplodedGraph"


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D82092.272007.patch
Type: text/x-patch
Size: 3179 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20200619/6a7c88fc/attachment-0001.bin>