DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Header

Mercurial (fddffdeab170)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265
/* -*- Mode: C++; tab-width: 8; indent-tabs-mode: nil; c-basic-offset: 4 -*-
 * vim: set ts=8 sts=4 et sw=4 tw=99: */

// Copyright 2012 the V8 project authors. All rights reserved.
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//     * Redistributions of source code must retain the above copyright
//       notice, this list of conditions and the following disclaimer.
//     * Redistributions in binary form must reproduce the above
//       copyright notice, this list of conditions and the following
//       disclaimer in the documentation and/or other materials provided
//       with the distribution.
//     * Neither the name of Google Inc. nor the names of its
//       contributors may be used to endorse or promote products derived
//       from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#include "irregexp/RegExpAST.h"

using namespace js;
using namespace js::irregexp;

#define MAKE_ACCEPT(Name)                                            \
  void* RegExp##Name::Accept(RegExpVisitor* visitor, void* data) {   \
    return visitor->Visit##Name(this, data);                         \
  }
FOR_EACH_REG_EXP_TREE_TYPE(MAKE_ACCEPT)
#undef MAKE_ACCEPT

#define MAKE_TYPE_CASE(Name)                                         \
  RegExp##Name* RegExpTree::As##Name() {                             \
    return nullptr;                                                  \
  }                                                                  \
  bool RegExpTree::Is##Name() { return false; }
FOR_EACH_REG_EXP_TREE_TYPE(MAKE_TYPE_CASE)
#undef MAKE_TYPE_CASE

#define MAKE_TYPE_CASE(Name)                                        \
  RegExp##Name* RegExp##Name::As##Name() {                          \
    return this;                                                    \
  }                                                                 \
  bool RegExp##Name::Is##Name() { return true; }
FOR_EACH_REG_EXP_TREE_TYPE(MAKE_TYPE_CASE)
#undef MAKE_TYPE_CASE

static Interval
ListCaptureRegisters(const RegExpTreeVector& children)
{
    Interval result = Interval::Empty();
    for (size_t i = 0; i < children.length(); i++)
        result = result.Union(children[i]->CaptureRegisters());
    return result;
}

// ----------------------------------------------------------------------------
// RegExpDisjunction

RegExpDisjunction::RegExpDisjunction(RegExpTreeVector* alternatives)
  : alternatives_(alternatives)
{
    MOZ_ASSERT(alternatives->length() > 1);
    RegExpTree* first_alternative = (*alternatives)[0];
    min_match_ = first_alternative->min_match();
    max_match_ = first_alternative->max_match();
    for (size_t i = 1; i < alternatives->length(); i++) {
        RegExpTree* alternative = (*alternatives)[i];
        min_match_ = Min(min_match_, alternative->min_match());
        max_match_ = Max(max_match_, alternative->max_match());
    }
}

Interval
RegExpDisjunction::CaptureRegisters()
{
    return ListCaptureRegisters(alternatives());
}

bool
RegExpDisjunction::IsAnchoredAtStart()
{
    const RegExpTreeVector& alternatives = this->alternatives();
    for (size_t i = 0; i < alternatives.length(); i++) {
        if (!alternatives[i]->IsAnchoredAtStart())
            return false;
    }
    return true;
}

bool
RegExpDisjunction::IsAnchoredAtEnd()
{
    const RegExpTreeVector& alternatives = this->alternatives();
    for (size_t i = 0; i < alternatives.length(); i++) {
        if (!alternatives[i]->IsAnchoredAtEnd())
            return false;
    }
    return true;
}

// ----------------------------------------------------------------------------
// RegExpAlternative

static int IncreaseBy(int previous, int increase)
{
    if (RegExpTree::kInfinity - previous < increase)
        return RegExpTree::kInfinity;
    return previous + increase;
}

RegExpAlternative::RegExpAlternative(RegExpTreeVector* nodes)
  : nodes_(nodes),
    min_match_(0),
    max_match_(0)
{
    MOZ_ASSERT(nodes->length() > 1);
    for (size_t i = 0; i < nodes->length(); i++) {
        RegExpTree* node = (*nodes)[i];
        int node_min_match = node->min_match();
        min_match_ = IncreaseBy(min_match_, node_min_match);
        int node_max_match = node->max_match();
        max_match_ = IncreaseBy(max_match_, node_max_match);
    }
}

Interval
RegExpAlternative::CaptureRegisters()
{
    return ListCaptureRegisters(nodes());
}

bool
RegExpAlternative::IsAnchoredAtStart()
{
    const RegExpTreeVector& nodes = this->nodes();
    for (size_t i = 0; i < nodes.length(); i++) {
        RegExpTree* node = nodes[i];
        if (node->IsAnchoredAtStart()) { return true; }
        if (node->max_match() > 0) { return false; }
    }
    return false;
}

bool
RegExpAlternative::IsAnchoredAtEnd()
{
    const RegExpTreeVector& nodes = this->nodes();
    for (int i = nodes.length() - 1; i >= 0; i--) {
        RegExpTree* node = nodes[i];
        if (node->IsAnchoredAtEnd()) { return true; }
        if (node->max_match() > 0) { return false; }
    }
    return false;
}

// ----------------------------------------------------------------------------
// RegExpAssertion

bool
RegExpAssertion::IsAnchoredAtStart()
{
    return assertion_type() == RegExpAssertion::START_OF_INPUT;
}

bool
RegExpAssertion::IsAnchoredAtEnd()
{
    return assertion_type() == RegExpAssertion::END_OF_INPUT;
}

// ----------------------------------------------------------------------------
// RegExpCharacterClass

void
RegExpCharacterClass::AppendToText(RegExpText* text)
{
    text->AddElement(TextElement::CharClass(this));
}

CharacterRangeVector&
CharacterSet::ranges(LifoAlloc* alloc)
{
    if (ranges_ == nullptr) {
        ranges_ = alloc->newInfallible<CharacterRangeVector>(*alloc);
        CharacterRange::AddClassEscape(alloc, standard_set_type_, ranges_);
    }
    return *ranges_;
}

// ----------------------------------------------------------------------------
// RegExpAtom

void
RegExpAtom::AppendToText(RegExpText* text)
{
    text->AddElement(TextElement::Atom(this));
}

// ----------------------------------------------------------------------------
// RegExpText

void
RegExpText::AppendToText(RegExpText* text)
{
    for (size_t i = 0; i < elements().length(); i++)
        text->AddElement(elements()[i]);
}

// ----------------------------------------------------------------------------
// RegExpQuantifier

Interval
RegExpQuantifier::CaptureRegisters()
{
    return body()->CaptureRegisters();
}

// ----------------------------------------------------------------------------
// RegExpCapture

bool
RegExpCapture::IsAnchoredAtStart()
{
    return body()->IsAnchoredAtStart();
}

bool
RegExpCapture::IsAnchoredAtEnd()
{
    return body()->IsAnchoredAtEnd();
}

Interval
RegExpCapture::CaptureRegisters()
{
    Interval self(StartRegister(index()), EndRegister(index()));
    return self.Union(body()->CaptureRegisters());
}

// ----------------------------------------------------------------------------
// RegExpLookahead

Interval
RegExpLookahead::CaptureRegisters()
{
    return body()->CaptureRegisters();
}

bool
RegExpLookahead::IsAnchoredAtStart()
{
    return is_positive() && body()->IsAnchoredAtStart();
}