Re-apply: Add python tool to dump and construct header maps

Header maps are binary files used by Xcode, which are used to map
header names or paths to other locations. Clang has support for
those since its inception, but there's not a lot of header map
testing around.

Since it's a binary format, testing becomes pretty much brittle
and its hard to even know what's inside if you don't have the
appropriate tools.

Add a python based tool that allows creating and dumping header
maps based on a json description of those. While here, rewrite
tests to use the tool and remove the binary files from the tree.

This tool was initially written by Daniel Dunbar.

Thanks to Stella Stamenova for helping make this work on Windows.

Differential Revision: https://reviews.llvm.org/D46485

rdar://problem/39994722

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@335295 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 312 insertions, 0 deletions

diff --git a/utils/hmaptool/CMakeLists.txt b/utils/hmaptool/CMakeLists.txt
new file mode 100644
index 0000000000..5573009d34
--- /dev/null
+++ b/utils/hmaptool/CMakeLists.txt
@@ -0,0 +1,16 @@
+set(CLANG_HMAPTOOL hmaptool)
+
+add_custom_command(OUTPUT ${CMAKE_BINARY_DIR}/${CMAKE_CFG_INTDIR}/bin/${CLANG_HMAPTOOL}
+                   COMMAND ${CMAKE_COMMAND} -E make_directory
+                     ${CMAKE_BINARY_DIR}/${CMAKE_CFG_INTDIR}/bin
+                   COMMAND ${CMAKE_COMMAND} -E copy
+                     ${CMAKE_CURRENT_SOURCE_DIR}/${CLANG_HMAPTOOL}
+                     ${CMAKE_BINARY_DIR}/${CMAKE_CFG_INTDIR}/bin/
+                   DEPENDS ${CMAKE_CURRENT_SOURCE_DIR}/${CLANG_HMAPTOOL})
+
+list(APPEND Depends ${CMAKE_BINARY_DIR}/${CMAKE_CFG_INTDIR}/bin/${CLANG_HMAPTOOL})
+install(PROGRAMS ${CLANG_HMAPTOOL} DESTINATION bin)
+
+add_custom_target(hmaptool ALL DEPENDS ${Depends})
+set_target_properties(hmaptool PROPERTIES FOLDER "Utils")
+
diff --git a/utils/hmaptool/hmaptool b/utils/hmaptool/hmaptool
new file mode 100755
index 0000000000..2b1ca7436c
--- /dev/null
+++ b/utils/hmaptool/hmaptool
@@ -0,0 +1,296 @@
+#!/usr/bin/env python
+from __future__ import print_function
+
+import json
+import optparse
+import os
+import struct
+import sys
+
+###
+
+k_header_magic_LE = 'pamh'
+k_header_magic_BE = 'hmap'
+
+def hmap_hash(str):
+    """hash(str) -> int
+
+    Apply the "well-known" headermap hash function.
+    """
+
+    return sum((ord(c.lower()) * 13
+                for c in str), 0)
+
+class HeaderMap(object):
+    @staticmethod
+    def frompath(path):
+        with open(path, 'rb') as f:
+            magic = f.read(4)
+            if magic == k_header_magic_LE:
+                endian_code = '<'
+            elif magic == k_header_magic_BE:
+                endian_code = '>'
+            else:
+                raise SystemExit("error: %s: not a headermap" % (
+                        path,))
+
+            # Read the header information.
+            header_fmt = endian_code + 'HHIIII'
+            header_size = struct.calcsize(header_fmt)
+            data = f.read(header_size)
+            if len(data) != header_size:
+                raise SystemExit("error: %s: truncated headermap header" % (
+                        path,))
+
+            (version, reserved, strtable_offset, num_entries,
+             num_buckets, max_value_len) = struct.unpack(header_fmt, data)
+
+            if version != 1:
+                raise SystemExit("error: %s: unknown headermap version: %r" % (
+                        path, version))
+            if reserved != 0:
+                raise SystemExit("error: %s: invalid reserved value in header" % (
+                        path,))
+
+            # The number of buckets must be a power of two.
+            if num_buckets == 0 or (num_buckets & num_buckets - 1) != 0:
+                raise SystemExit("error: %s: invalid number of buckets" % (
+                        path,))
+
+            # Read all of the buckets.
+            bucket_fmt = endian_code + 'III'
+            bucket_size = struct.calcsize(bucket_fmt)
+            buckets_data = f.read(num_buckets * bucket_size)
+            if len(buckets_data) != num_buckets * bucket_size:
+                raise SystemExit("error: %s: truncated headermap buckets" % (
+                        path,))
+            buckets = [struct.unpack(bucket_fmt,
+                                     buckets_data[i*bucket_size:(i+1)*bucket_size])
+                       for i in range(num_buckets)]
+
+            # Read the string table; the format doesn't explicitly communicate the
+            # size of the string table (which is dumb), so assume it is the rest of
+            # the file.
+            f.seek(0, 2)
+            strtable_size = f.tell() - strtable_offset
+            f.seek(strtable_offset)
+
+            if strtable_size == 0:
+                raise SystemExit("error: %s: unable to read zero-sized string table"%(
+                        path,))
+            strtable = f.read(strtable_size)
+
+            if len(strtable) != strtable_size:
+                raise SystemExit("error: %s: unable to read complete string table"%(
+                        path,))
+            if strtable[-1] != '\0':
+                raise SystemExit("error: %s: invalid string table in headermap" % (
+                        path,))
+
+            return HeaderMap(num_entries, buckets, strtable)
+
+    def __init__(self, num_entries, buckets, strtable):
+        self.num_entries = num_entries
+        self.buckets = buckets
+        self.strtable = strtable
+
+    def get_string(self, idx):
+        if idx >= len(self.strtable):
+            raise SystemExit("error: %s: invalid string index" % (
+                    path,))
+        end_idx = self.strtable.index('\0', idx)
+        return self.strtable[idx:end_idx]
+
+    @property
+    def mappings(self):
+        for key_idx,prefix_idx,suffix_idx in self.buckets:
+            if key_idx == 0:
+                continue
+            yield (self.get_string(key_idx),
+                   self.get_string(prefix_idx) + self.get_string(suffix_idx))
+
+###
+
+def action_dump(name, args):
+    "dump a headermap file"
+
+    parser = optparse.OptionParser("%%prog %s [options] <headermap path>" % (
+            name,))
+    parser.add_option("-v", "--verbose", dest="verbose",
+                      help="show more verbose output [%default]",
+                      action="store_true", default=False)
+    (opts, args) = parser.parse_args(args)
+
+    if len(args) != 1:
+        parser.error("invalid number of arguments")
+
+    path, = args
+
+    hmap = HeaderMap.frompath(path)
+
+    # Dump all of the buckets.
+    print ('Header Map: %s' % (path,))
+    if opts.verbose:
+        print ('headermap: %r' % (path,))
+        print ('  num entries: %d' % (hmap.num_entries,))
+        print ('  num buckets: %d' % (len(hmap.buckets),))
+        print ('  string table size: %d' % (len(hmap.strtable),))
+        for i,bucket in enumerate(hmap.buckets):
+            key_idx,prefix_idx,suffix_idx = bucket
+
+            if key_idx == 0:
+                continue
+
+            # Get the strings.
+            key = hmap.get_string(key_idx)
+            prefix = hmap.get_string(prefix_idx)
+            suffix = hmap.get_string(suffix_idx)
+
+            print ("  bucket[%d]: %r -> (%r, %r) -- %d" % (
+                i, key, prefix, suffix, (hmap_hash(key) & (num_buckets - 1))))
+    else:
+        mappings = sorted(hmap.mappings)
+        for key,value in mappings:
+            print ("%s -> %s" % (key, value))
+    print ()
+
+def next_power_of_two(value):
+    if value < 0:
+        raise ArgumentError
+    return 1 if value == 0 else 2**(value - 1).bit_length()
+
+def action_write(name, args):
+    "write a headermap file from a JSON definition"
+
+    parser = optparse.OptionParser("%%prog %s [options] <input path> <output path>" % (
+            name,))
+    (opts, args) = parser.parse_args(args)
+
+    if len(args) != 2:
+        parser.error("invalid number of arguments")
+
+    input_path,output_path = args
+
+    with open(input_path, "r") as f:
+        input_data = json.load(f)
+
+    # Compute the headermap contents, we make a table that is 1/3 full.
+    mappings = input_data['mappings']
+    num_buckets = next_power_of_two(len(mappings) * 3)
+
+    table = [(0, 0, 0)
+             for i in range(num_buckets)]
+    max_value_len = 0
+    strtable = "\0"
+    for key,value in mappings.items():
+        if not isinstance(key, str):
+            key = key.decode('utf-8')
+        if not isinstance(value, str):
+            value = value.decode('utf-8')
+        max_value_len = max(max_value_len, len(value))
+
+        key_idx = len(strtable)
+        strtable += key + '\0'
+        prefix = os.path.dirname(value) + '/'
+        suffix = os.path.basename(value)
+        prefix_idx = len(strtable)
+        strtable += prefix + '\0'
+        suffix_idx = len(strtable)
+        strtable += suffix + '\0'
+
+        hash = hmap_hash(key)
+        for i in range(num_buckets):
+            idx = (hash + i) % num_buckets
+            if table[idx][0] == 0:
+                table[idx] = (key_idx, prefix_idx, suffix_idx)
+                break
+        else:
+            raise RuntimeError
+
+    endian_code = '<'
+    magic = k_header_magic_LE
+    magic_size = 4
+    header_fmt = endian_code + 'HHIIII'
+    header_size = struct.calcsize(header_fmt)
+    bucket_fmt = endian_code + 'III'
+    bucket_size = struct.calcsize(bucket_fmt)
+    strtable_offset = magic_size + header_size + num_buckets * bucket_size
+    header = (1, 0, strtable_offset, len(mappings),
+              num_buckets, max_value_len)
+
+    # Write out the headermap.
+    with open(output_path, 'wb') as f:
+        f.write(magic.encode())
+        f.write(struct.pack(header_fmt, *header))
+        for bucket in table:
+            f.write(struct.pack(bucket_fmt, *bucket))
+        f.write(strtable.encode())
+
+def action_tovfs(name, args):
+    "convert a headermap to a VFS layout"
+
+    parser = optparse.OptionParser("%%prog %s [options] <headermap path>" % (
+            name,))
+    parser.add_option("", "--build-path", dest="build_path",
+                      help="build path prefix",
+                      action="store", type=str)
+    (opts, args) = parser.parse_args(args)
+
+    if len(args) != 2:
+        parser.error("invalid number of arguments")
+    if opts.build_path is None:
+        parser.error("--build-path is required")
+
+    input_path,output_path = args
+
+    hmap = HeaderMap.frompath(input_path)
+
+    # Create the table for all the objects.
+    vfs = {}
+    vfs['version'] = 0
+    build_dir_contents = []
+    vfs['roots'] = [{
+            'name' : opts.build_path,
+            'type' : 'directory',
+            'contents' : build_dir_contents }]
+
+    # We assume we are mapping framework paths, so a key of "Foo/Bar.h" maps to
+    # "<build path>/Foo.framework/Headers/Bar.h".
+    for key,value in hmap.mappings:
+        # If this isn't a framework style mapping, ignore it.
+        components = key.split('/')
+        if len(components) != 2:
+            continue
+        framework_name,header_name = components
+        build_dir_contents.append({
+                'name' : '%s.framework/Headers/%s' % (framework_name,
+                                                      header_name),
+                'type' : 'file',
+                'external-contents' : value })
+
+    with open(output_path, 'w') as f:
+        json.dump(vfs, f, indent=2)
+
+commands = dict((name[7:].replace("_","-"), f)
+                for name,f in locals().items()
+                if name.startswith('action_'))
+
+def usage():
+    print ("Usage: %s command [options]" % (
+        os.path.basename(sys.argv[0])), file=sys.stderr)
+    print (file=sys.stderr)
+    print ("Available commands:", file=sys.stderr)
+    cmds_width = max(map(len, commands))
+    for name,func in sorted(commands.items()):
+        print ("  %-*s - %s" % (cmds_width, name, func.__doc__), file=sys.stderr)
+    sys.exit(1)
+
+def main():
+    if len(sys.argv) < 2 or sys.argv[1] not in commands:
+        usage()
+
+    cmd = sys.argv[1]
+    commands[cmd](cmd, sys.argv[2:])
+
+if __name__ == '__main__':
+    main()