grpc 1.30.2 → 1.32.0

data/third_party/re2/re2/stringpiece.cc

@@ -0,0 +1,65 @@
+// Copyright 2004 The RE2 Authors.  All Rights Reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+#include "re2/stringpiece.h"
+
+#include <ostream>
+
+#include "util/util.h"
+
+namespace re2 {
+
+const StringPiece::size_type StringPiece::npos;  // initialized in stringpiece.h
+
+StringPiece::size_type StringPiece::copy(char* buf, size_type n,
+                                         size_type pos) const {
+  size_type ret = std::min(size_ - pos, n);
+  memcpy(buf, data_ + pos, ret);
+  return ret;
+}
+
+StringPiece StringPiece::substr(size_type pos, size_type n) const {
+  if (pos > size_) pos = size_;
+  if (n > size_ - pos) n = size_ - pos;
+  return StringPiece(data_ + pos, n);
+}
+
+StringPiece::size_type StringPiece::find(const StringPiece& s,
+                                         size_type pos) const {
+  if (pos > size_) return npos;
+  const_pointer result = std::search(data_ + pos, data_ + size_,
+                                     s.data_, s.data_ + s.size_);
+  size_type xpos = result - data_;
+  return xpos + s.size_ <= size_ ? xpos : npos;
+}
+
+StringPiece::size_type StringPiece::find(char c, size_type pos) const {
+  if (size_ <= 0 || pos >= size_) return npos;
+  const_pointer result = std::find(data_ + pos, data_ + size_, c);
+  return result != data_ + size_ ? result - data_ : npos;
+}
+
+StringPiece::size_type StringPiece::rfind(const StringPiece& s,
+                                          size_type pos) const {
+  if (size_ < s.size_) return npos;
+  if (s.size_ == 0) return std::min(size_, pos);
+  const_pointer last = data_ + std::min(size_ - s.size_, pos) + s.size_;
+  const_pointer result = std::find_end(data_, last, s.data_, s.data_ + s.size_);
+  return result != last ? result - data_ : npos;
+}
+
+StringPiece::size_type StringPiece::rfind(char c, size_type pos) const {
+  if (size_ <= 0) return npos;
+  for (size_t i = std::min(pos + 1, size_); i != 0;) {
+    if (data_[--i] == c) return i;
+  }
+  return npos;
+}
+
+std::ostream& operator<<(std::ostream& o, const StringPiece& p) {
+  o.write(p.data(), p.size());
+  return o;
+}
+
+}  // namespace re2

data/third_party/re2/re2/stringpiece.h

@@ -0,0 +1,210 @@
+// Copyright 2001-2010 The RE2 Authors.  All Rights Reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+#ifndef RE2_STRINGPIECE_H_
+#define RE2_STRINGPIECE_H_
+
+// A string-like object that points to a sized piece of memory.
+//
+// Functions or methods may use const StringPiece& parameters to accept either
+// a "const char*" or a "string" value that will be implicitly converted to
+// a StringPiece.  The implicit conversion means that it is often appropriate
+// to include this .h file in other files rather than forward-declaring
+// StringPiece as would be appropriate for most other Google classes.
+//
+// Systematic usage of StringPiece is encouraged as it will reduce unnecessary
+// conversions from "const char*" to "string" and back again.
+//
+//
+// Arghh!  I wish C++ literals were "string".
+
+// Doing this simplifies the logic below.
+#ifndef __has_include
+#define __has_include(x) 0
+#endif
+
+#include <stddef.h>
+#include <string.h>
+#include <algorithm>
+#include <iosfwd>
+#include <iterator>
+#include <string>
+#if __has_include(<string_view>) && __cplusplus >= 201703L
+#include <string_view>
+#endif
+
+namespace re2 {
+
+class StringPiece {
+ public:
+  typedef std::char_traits<char> traits_type;
+  typedef char value_type;
+  typedef char* pointer;
+  typedef const char* const_pointer;
+  typedef char& reference;
+  typedef const char& const_reference;
+  typedef const char* const_iterator;
+  typedef const_iterator iterator;
+  typedef std::reverse_iterator<const_iterator> const_reverse_iterator;
+  typedef const_reverse_iterator reverse_iterator;
+  typedef size_t size_type;
+  typedef ptrdiff_t difference_type;
+  static const size_type npos = static_cast<size_type>(-1);
+
+  // We provide non-explicit singleton constructors so users can pass
+  // in a "const char*" or a "string" wherever a "StringPiece" is
+  // expected.
+  StringPiece()
+      : data_(NULL), size_(0) {}
+#if __has_include(<string_view>) && __cplusplus >= 201703L
+  StringPiece(const std::string_view& str)
+      : data_(str.data()), size_(str.size()) {}
+#endif
+  StringPiece(const std::string& str)
+      : data_(str.data()), size_(str.size()) {}
+  StringPiece(const char* str)
+      : data_(str), size_(str == NULL ? 0 : strlen(str)) {}
+  StringPiece(const char* str, size_type len)
+      : data_(str), size_(len) {}
+
+  const_iterator begin() const { return data_; }
+  const_iterator end() const { return data_ + size_; }
+  const_reverse_iterator rbegin() const {
+    return const_reverse_iterator(data_ + size_);
+  }
+  const_reverse_iterator rend() const {
+    return const_reverse_iterator(data_);
+  }
+
+  size_type size() const { return size_; }
+  size_type length() const { return size_; }
+  bool empty() const { return size_ == 0; }
+
+  const_reference operator[](size_type i) const { return data_[i]; }
+  const_pointer data() const { return data_; }
+
+  void remove_prefix(size_type n) {
+    data_ += n;
+    size_ -= n;
+  }
+
+  void remove_suffix(size_type n) {
+    size_ -= n;
+  }
+
+  void set(const char* str) {
+    data_ = str;
+    size_ = str == NULL ? 0 : strlen(str);
+  }
+
+  void set(const char* str, size_type len) {
+    data_ = str;
+    size_ = len;
+  }
+
+  // Converts to `std::basic_string`.
+  template <typename A>
+  explicit operator std::basic_string<char, traits_type, A>() const {
+    if (!data_) return {};
+    return std::basic_string<char, traits_type, A>(data_, size_);
+  }
+
+  std::string as_string() const {
+    return std::string(data_, size_);
+  }
+
+  // We also define ToString() here, since many other string-like
+  // interfaces name the routine that converts to a C++ string
+  // "ToString", and it's confusing to have the method that does that
+  // for a StringPiece be called "as_string()".  We also leave the
+  // "as_string()" method defined here for existing code.
+  std::string ToString() const {
+    return std::string(data_, size_);
+  }
+
+  void CopyToString(std::string* target) const {
+    target->assign(data_, size_);
+  }
+
+  void AppendToString(std::string* target) const {
+    target->append(data_, size_);
+  }
+
+  size_type copy(char* buf, size_type n, size_type pos = 0) const;
+  StringPiece substr(size_type pos = 0, size_type n = npos) const;
+
+  int compare(const StringPiece& x) const {
+    size_type min_size = std::min(size(), x.size());
+    if (min_size > 0) {
+      int r = memcmp(data(), x.data(), min_size);
+      if (r < 0) return -1;
+      if (r > 0) return 1;
+    }
+    if (size() < x.size()) return -1;
+    if (size() > x.size()) return 1;
+    return 0;
+  }
+
+  // Does "this" start with "x"?
+  bool starts_with(const StringPiece& x) const {
+    return x.empty() ||
+           (size() >= x.size() && memcmp(data(), x.data(), x.size()) == 0);
+  }
+
+  // Does "this" end with "x"?
+  bool ends_with(const StringPiece& x) const {
+    return x.empty() ||
+           (size() >= x.size() &&
+            memcmp(data() + (size() - x.size()), x.data(), x.size()) == 0);
+  }
+
+  bool contains(const StringPiece& s) const {
+    return find(s) != npos;
+  }
+
+  size_type find(const StringPiece& s, size_type pos = 0) const;
+  size_type find(char c, size_type pos = 0) const;
+  size_type rfind(const StringPiece& s, size_type pos = npos) const;
+  size_type rfind(char c, size_type pos = npos) const;
+
+ private:
+  const_pointer data_;
+  size_type size_;
+};
+
+inline bool operator==(const StringPiece& x, const StringPiece& y) {
+  StringPiece::size_type len = x.size();
+  if (len != y.size()) return false;
+  return x.data() == y.data() || len == 0 ||
+         memcmp(x.data(), y.data(), len) == 0;
+}
+
+inline bool operator!=(const StringPiece& x, const StringPiece& y) {
+  return !(x == y);
+}
+
+inline bool operator<(const StringPiece& x, const StringPiece& y) {
+  StringPiece::size_type min_size = std::min(x.size(), y.size());
+  int r = min_size == 0 ? 0 : memcmp(x.data(), y.data(), min_size);
+  return (r < 0) || (r == 0 && x.size() < y.size());
+}
+
+inline bool operator>(const StringPiece& x, const StringPiece& y) {
+  return y < x;
+}
+
+inline bool operator<=(const StringPiece& x, const StringPiece& y) {
+  return !(x > y);
+}
+
+inline bool operator>=(const StringPiece& x, const StringPiece& y) {
+  return !(x < y);
+}
+
+// Allow StringPiece to be logged.
+std::ostream& operator<<(std::ostream& o, const StringPiece& p);
+
+}  // namespace re2
+
+#endif  // RE2_STRINGPIECE_H_

data/third_party/re2/re2/tostring.cc

@@ -0,0 +1,351 @@
+// Copyright 2006 The RE2 Authors.  All Rights Reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+// Format a regular expression structure as a string.
+// Tested by parse_test.cc
+
+#include <string.h>
+#include <string>
+
+#include "util/util.h"
+#include "util/logging.h"
+#include "util/strutil.h"
+#include "util/utf.h"
+#include "re2/regexp.h"
+#include "re2/walker-inl.h"
+
+namespace re2 {
+
+enum {
+  PrecAtom,
+  PrecUnary,
+  PrecConcat,
+  PrecAlternate,
+  PrecEmpty,
+  PrecParen,
+  PrecToplevel,
+};
+
+// Helper function.  See description below.
+static void AppendCCRange(std::string* t, Rune lo, Rune hi);
+
+// Walker to generate string in s_.
+// The arg pointers are actually integers giving the
+// context precedence.
+// The child_args are always NULL.
+class ToStringWalker : public Regexp::Walker<int> {
+ public:
+  explicit ToStringWalker(std::string* t) : t_(t) {}
+
+  virtual int PreVisit(Regexp* re, int parent_arg, bool* stop);
+  virtual int PostVisit(Regexp* re, int parent_arg, int pre_arg,
+                        int* child_args, int nchild_args);
+  virtual int ShortVisit(Regexp* re, int parent_arg) {
+    return 0;
+  }
+
+ private:
+  std::string* t_;  // The string the walker appends to.
+
+  ToStringWalker(const ToStringWalker&) = delete;
+  ToStringWalker& operator=(const ToStringWalker&) = delete;
+};
+
+std::string Regexp::ToString() {
+  std::string t;
+  ToStringWalker w(&t);
+  w.WalkExponential(this, PrecToplevel, 100000);
+  if (w.stopped_early())
+    t += " [truncated]";
+  return t;
+}
+
+#define ToString DontCallToString  // Avoid accidental recursion.
+
+// Visits re before children are processed.
+// Appends ( if needed and passes new precedence to children.
+int ToStringWalker::PreVisit(Regexp* re, int parent_arg, bool* stop) {
+  int prec = parent_arg;
+  int nprec = PrecAtom;
+
+  switch (re->op()) {
+    case kRegexpNoMatch:
+    case kRegexpEmptyMatch:
+    case kRegexpLiteral:
+    case kRegexpAnyChar:
+    case kRegexpAnyByte:
+    case kRegexpBeginLine:
+    case kRegexpEndLine:
+    case kRegexpBeginText:
+    case kRegexpEndText:
+    case kRegexpWordBoundary:
+    case kRegexpNoWordBoundary:
+    case kRegexpCharClass:
+    case kRegexpHaveMatch:
+      nprec = PrecAtom;
+      break;
+
+    case kRegexpConcat:
+    case kRegexpLiteralString:
+      if (prec < PrecConcat)
+        t_->append("(?:");
+      nprec = PrecConcat;
+      break;
+
+    case kRegexpAlternate:
+      if (prec < PrecAlternate)
+        t_->append("(?:");
+      nprec = PrecAlternate;
+      break;
+
+    case kRegexpCapture:
+      t_->append("(");
+      if (re->cap() == 0)
+        LOG(DFATAL) << "kRegexpCapture cap() == 0";
+      if (re->name()) {
+        t_->append("?P<");
+        t_->append(*re->name());
+        t_->append(">");
+      }
+      nprec = PrecParen;
+      break;
+
+    case kRegexpStar:
+    case kRegexpPlus:
+    case kRegexpQuest:
+    case kRegexpRepeat:
+      if (prec < PrecUnary)
+        t_->append("(?:");
+      // The subprecedence here is PrecAtom instead of PrecUnary
+      // because PCRE treats two unary ops in a row as a parse error.
+      nprec = PrecAtom;
+      break;
+  }
+
+  return nprec;
+}
+
+static void AppendLiteral(std::string *t, Rune r, bool foldcase) {
+  if (r != 0 && r < 0x80 && strchr("(){}[]*+?|.^$\\", r)) {
+    t->append(1, '\\');
+    t->append(1, static_cast<char>(r));
+  } else if (foldcase && 'a' <= r && r <= 'z') {
+    r -= 'a' - 'A';
+    t->append(1, '[');
+    t->append(1, static_cast<char>(r));
+    t->append(1, static_cast<char>(r) + 'a' - 'A');
+    t->append(1, ']');
+  } else {
+    AppendCCRange(t, r, r);
+  }
+}
+
+// Visits re after children are processed.
+// For childless regexps, all the work is done here.
+// For regexps with children, append any unary suffixes or ).
+int ToStringWalker::PostVisit(Regexp* re, int parent_arg, int pre_arg,
+                              int* child_args, int nchild_args) {
+  int prec = parent_arg;
+  switch (re->op()) {
+    case kRegexpNoMatch:
+      // There's no simple symbol for "no match", but
+      // [^0-Runemax] excludes everything.
+      t_->append("[^\\x00-\\x{10ffff}]");
+      break;
+
+    case kRegexpEmptyMatch:
+      // Append (?:) to make empty string visible,
+      // unless this is already being parenthesized.
+      if (prec < PrecEmpty)
+        t_->append("(?:)");
+      break;
+
+    case kRegexpLiteral:
+      AppendLiteral(t_, re->rune(),
+                    (re->parse_flags() & Regexp::FoldCase) != 0);
+      break;
+
+    case kRegexpLiteralString:
+      for (int i = 0; i < re->nrunes(); i++)
+        AppendLiteral(t_, re->runes()[i],
+                      (re->parse_flags() & Regexp::FoldCase) != 0);
+      if (prec < PrecConcat)
+        t_->append(")");
+      break;
+
+    case kRegexpConcat:
+      if (prec < PrecConcat)
+        t_->append(")");
+      break;
+
+    case kRegexpAlternate:
+      // Clumsy but workable: the children all appended |
+      // at the end of their strings, so just remove the last one.
+      if ((*t_)[t_->size()-1] == '|')
+        t_->erase(t_->size()-1);
+      else
+        LOG(DFATAL) << "Bad final char: " << t_;
+      if (prec < PrecAlternate)
+        t_->append(")");
+      break;
+
+    case kRegexpStar:
+      t_->append("*");
+      if (re->parse_flags() & Regexp::NonGreedy)
+        t_->append("?");
+      if (prec < PrecUnary)
+        t_->append(")");
+      break;
+
+    case kRegexpPlus:
+      t_->append("+");
+      if (re->parse_flags() & Regexp::NonGreedy)
+        t_->append("?");
+      if (prec < PrecUnary)
+        t_->append(")");
+      break;
+
+    case kRegexpQuest:
+      t_->append("?");
+      if (re->parse_flags() & Regexp::NonGreedy)
+        t_->append("?");
+      if (prec < PrecUnary)
+        t_->append(")");
+      break;
+
+    case kRegexpRepeat:
+      if (re->max() == -1)
+        t_->append(StringPrintf("{%d,}", re->min()));
+      else if (re->min() == re->max())
+        t_->append(StringPrintf("{%d}", re->min()));
+      else
+        t_->append(StringPrintf("{%d,%d}", re->min(), re->max()));
+      if (re->parse_flags() & Regexp::NonGreedy)
+        t_->append("?");
+      if (prec < PrecUnary)
+        t_->append(")");
+      break;
+
+    case kRegexpAnyChar:
+      t_->append(".");
+      break;
+
+    case kRegexpAnyByte:
+      t_->append("\\C");
+      break;
+
+    case kRegexpBeginLine:
+      t_->append("^");
+      break;
+
+    case kRegexpEndLine:
+      t_->append("$");
+      break;
+
+    case kRegexpBeginText:
+      t_->append("(?-m:^)");
+      break;
+
+    case kRegexpEndText:
+      if (re->parse_flags() & Regexp::WasDollar)
+        t_->append("(?-m:$)");
+      else
+        t_->append("\\z");
+      break;
+
+    case kRegexpWordBoundary:
+      t_->append("\\b");
+      break;
+
+    case kRegexpNoWordBoundary:
+      t_->append("\\B");
+      break;
+
+    case kRegexpCharClass: {
+      if (re->cc()->size() == 0) {
+        t_->append("[^\\x00-\\x{10ffff}]");
+        break;
+      }
+      t_->append("[");
+      // Heuristic: show class as negated if it contains the
+      // non-character 0xFFFE and yet somehow isn't full.
+      CharClass* cc = re->cc();
+      if (cc->Contains(0xFFFE) && !cc->full()) {
+        cc = cc->Negate();
+        t_->append("^");
+      }
+      for (CharClass::iterator i = cc->begin(); i != cc->end(); ++i)
+        AppendCCRange(t_, i->lo, i->hi);
+      if (cc != re->cc())
+        cc->Delete();
+      t_->append("]");
+      break;
+    }
+
+    case kRegexpCapture:
+      t_->append(")");
+      break;
+
+    case kRegexpHaveMatch:
+      // There's no syntax accepted by the parser to generate
+      // this node (it is generated by RE2::Set) so make something
+      // up that is readable but won't compile.
+      t_->append("(?HaveMatch:%d)", re->match_id());
+      break;
+  }
+
+  // If the parent is an alternation, append the | for it.
+  if (prec == PrecAlternate)
+    t_->append("|");
+
+  return 0;
+}
+
+// Appends a rune for use in a character class to the string t.
+static void AppendCCChar(std::string* t, Rune r) {
+  if (0x20 <= r && r <= 0x7E) {
+    if (strchr("[]^-\\", r))
+      t->append("\\");
+    t->append(1, static_cast<char>(r));
+    return;
+  }
+  switch (r) {
+    default:
+      break;
+
+    case '\r':
+      t->append("\\r");
+      return;
+
+    case '\t':
+      t->append("\\t");
+      return;
+
+    case '\n':
+      t->append("\\n");
+      return;
+
+    case '\f':
+      t->append("\\f");
+      return;
+  }
+
+  if (r < 0x100) {
+    *t += StringPrintf("\\x%02x", static_cast<int>(r));
+    return;
+  }
+  *t += StringPrintf("\\x{%x}", static_cast<int>(r));
+}
+
+static void AppendCCRange(std::string* t, Rune lo, Rune hi) {
+  if (lo > hi)
+    return;
+  AppendCCChar(t, lo);
+  if (lo < hi) {
+    t->append("-");
+    AppendCCChar(t, hi);
+  }
+}
+
+}  // namespace re2