[clangd] Using symbol name to map includes for STL symbols.

Summary:
Using suffix path mapping relies on the STL implementations, and it is
not portable. This patch is using symbol name mapping, which should
work with different STL implementations, fix clangd/clangd#9.

To generate the symbol mapping, we parse the cppreference symbol index
page to build a lookup table.

The mapping is not completed, a few TODOs:
  - support symbols from different headers (e.g. std::move)
  - support STL macros
  - support symbols from std's sub-namespaces (e.g. chrono)

Reviewers: ioeric, jfb, serge-sans-paille

Reviewed By: ioeric

Subscribers: sammccall, klimek, ilya-biryukov, ioeric, MaskRay, jkorous, mgrang, arphaman, kadircet, jfb, jdoerfert, cfe-commits

Tags: #clang-tools-extra, #clang

Differential Revision: https://reviews.llvm.org/D58345

llvm-svn: 356134

1 files changed, 101 insertions, 0 deletions

diff --git a/clang-tools-extra/clangd/include-mapping/test.py b/clang-tools-extra/clangd/include-mapping/test.py
new file mode 100755
index 00000000000..89fa359184c
--- /dev/null
+++ b/clang-tools-extra/clangd/include-mapping/test.py
@@ -0,0 +1,101 @@
+#!/usr/bin/env python
+#===- test.py -  ---------------------------------------------*- python -*--===#
+#
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+#
+#===------------------------------------------------------------------------===#
+
+from gen_std import ParseSymbolPage, ParseIndexPage
+
+import unittest
+
+class TestStdGen(unittest.TestCase):
+
+  def testParseIndexPage(self):
+    html = """
+ <a href="abs.html" title="abs"><tt>abs()</tt></a> (int) <br>
+ <a href="complex/abs.html" title="abs"><tt>abs&lt;&gt;()</tt></a> (std::complex) <br>
+ <a href="acos.html" title="acos"><tt>acos()</tt></a> <br>
+ <a href="acosh.html" title="acosh"><tt>acosh()</tt></a> <span class="t-mark-rev">(since C++11)</span> <br>
+ <a href="as_bytes.html" title="as bytes"><tt>as_bytes&lt;&gt;()</tt></a> <span class="t-mark-rev t-since-cxx20">(since C++20)</span> <br>
+ """
+
+    actual = ParseIndexPage(html)
+    expected = [
+      ("abs", "abs.html"),
+      ("abs", "complex/abs.html"),
+      ("acos", "acos.html"),
+      ("acosh", "acosh.html"),
+      ("as_bytes", "as_bytes.html"),
+    ]
+    self.assertEqual(len(actual), len(expected))
+    for i in range(0, len(actual)):
+      self.assertEqual(expected[i][0], actual[i][0])
+      self.assertTrue(actual[i][1].endswith(expected[i][1]))
+
+
+  def testParseSymbolPage_SingleHeader(self):
+    # Defined in header <cmath>
+    html = """
+ <table class="t-dcl-begin"><tbody>
+  <tr class="t-dsc-header">
+  <td> <div>Defined in header <code><a href="cmath.html" title="cmath">&lt;cmath&gt;</a></code>
+   </div></td>
+  <td></td>
+  <td></td>
+  </tr>
+</tbody></table>
+"""
+    self.assertEqual(ParseSymbolPage(html), ['<cmath>'])
+
+
+  def testParseSymbolPage_MulHeaders(self):
+    #  Defined in header <cstddef>
+    #  Defined in header <cstdio>
+    #  Defined in header <cstdlib>
+    html = """
+<table class="t-dcl-begin"><tbody>
+  <tr class="t-dsc-header">
+    <td> <div>Defined in header <code><a href="cstddef.html" title="cstddef">&lt;cstddef&gt;</a></code>
+     </div></td>
+     <td></td>
+    <td></td>
+  </tr>
+  <tr class="t-dsc-header">
+    <td> <div>Defined in header <code><a href="cstdio.html" title="cstdio">&lt;cstdio&gt;</a></code>
+     </div></td>
+    <td></td>
+    <td></td>
+  </tr>
+  <tr class="t-dsc-header">
+    <td> <div>Defined in header <code><a href=".cstdlib.html" title="ccstdlib">&lt;cstdlib&gt;</a></code>
+     </div></td>
+    <td></td>
+    <td></td>
+  </tr>
+</tbody></table>
+"""
+    self.assertEqual(ParseSymbolPage(html),
+                    ['<cstddef>', '<cstdio>', '<cstdlib>'])
+
+
+  def testParseSymbolPage_MulHeadersInSameDiv(self):
+    # Multile <code> blocks in a Div.
+    # Defined in header <algorithm>
+    # Defined in header <utility>
+    html = """
+<tr class="t-dsc-header">
+<td><div>
+     Defined in header <code><a href="../header/algorithm.html" title="cpp/header/algorithm">&lt;algorithm&gt;</a></code><br>
+     Defined in header <code><a href="../header/utility.html" title="cpp/header/utility">&lt;utility&gt;</a></code>
+</div></td>
+<td></td>
+</tr>
+"""
+    self.assertEqual(ParseSymbolPage(html), ['<algorithm>', '<utility>'])
+
+
+if __name__ == '__main__':
+  unittest.main()