1// © 2018 and later: Unicode, Inc. and others.
2// License & terms of use: http://www.unicode.org/copyright.html
3//
4// From the double-conversion library. Original license:
5//
6// Copyright 2012 the V8 project authors. All rights reserved.
7// Redistribution and use in source and binary forms, with or without
8// modification, are permitted provided that the following conditions are
9// met:
10//
11//     * Redistributions of source code must retain the above copyright
12//       notice, this list of conditions and the following disclaimer.
13//     * Redistributions in binary form must reproduce the above
14//       copyright notice, this list of conditions and the following
15//       disclaimer in the documentation and/or other materials provided
16//       with the distribution.
17//     * Neither the name of Google Inc. nor the names of its
18//       contributors may be used to endorse or promote products derived
19//       from this software without specific prior written permission.
20//
21// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32
33// ICU PATCH: ifdef around UCONFIG_NO_FORMATTING
34#include "unicode/utypes.h"
35#if !UCONFIG_NO_FORMATTING
36
37#ifndef DOUBLE_CONVERSION_STRING_TO_DOUBLE_H_
38#define DOUBLE_CONVERSION_STRING_TO_DOUBLE_H_
39
40// ICU PATCH: Customize header file paths for ICU.
41
42#include "double-conversion-utils.h"
43
44// ICU PATCH: Wrap in ICU namespace
45U_NAMESPACE_BEGIN
46
47namespace double_conversion {
48
49class StringToDoubleConverter {
50 public:
51  // Enumeration for allowing octals and ignoring junk when converting
52  // strings to numbers.
53  enum Flags {
54    NO_FLAGS = 0,
55    ALLOW_HEX = 1,
56    ALLOW_OCTALS = 2,
57    ALLOW_TRAILING_JUNK = 4,
58    ALLOW_LEADING_SPACES = 8,
59    ALLOW_TRAILING_SPACES = 16,
60    ALLOW_SPACES_AFTER_SIGN = 32,
61    ALLOW_CASE_INSENSITIVITY = 64,
62    ALLOW_CASE_INSENSIBILITY = 64,  // Deprecated
63    ALLOW_HEX_FLOATS = 128,
64  };
65
66  static const uc16 kNoSeparator = '\0';
67
68  // Flags should be a bit-or combination of the possible Flags-enum.
69  //  - NO_FLAGS: no special flags.
70  //  - ALLOW_HEX: recognizes the prefix "0x". Hex numbers may only be integers.
71  //      Ex: StringToDouble("0x1234") -> 4660.0
72  //          In StringToDouble("0x1234.56") the characters ".56" are trailing
73  //          junk. The result of the call is hence dependent on
74  //          the ALLOW_TRAILING_JUNK flag and/or the junk value.
75  //      With this flag "0x" is a junk-string. Even with ALLOW_TRAILING_JUNK,
76  //      the string will not be parsed as "0" followed by junk.
77  //
78  //  - ALLOW_OCTALS: recognizes the prefix "0" for octals:
79  //      If a sequence of octal digits starts with '0', then the number is
80  //      read as octal integer. Octal numbers may only be integers.
81  //      Ex: StringToDouble("01234") -> 668.0
82  //          StringToDouble("012349") -> 12349.0  // Not a sequence of octal
83  //                                               // digits.
84  //          In StringToDouble("01234.56") the characters ".56" are trailing
85  //          junk. The result of the call is hence dependent on
86  //          the ALLOW_TRAILING_JUNK flag and/or the junk value.
87  //          In StringToDouble("01234e56") the characters "e56" are trailing
88  //          junk, too.
89  //  - ALLOW_TRAILING_JUNK: ignore trailing characters that are not part of
90  //      a double literal.
91  //  - ALLOW_LEADING_SPACES: skip over leading whitespace, including spaces,
92  //                          new-lines, and tabs.
93  //  - ALLOW_TRAILING_SPACES: ignore trailing whitespace.
94  //  - ALLOW_SPACES_AFTER_SIGN: ignore whitespace after the sign.
95  //       Ex: StringToDouble("-   123.2") -> -123.2.
96  //           StringToDouble("+   123.2") -> 123.2
97  //  - ALLOW_CASE_INSENSITIVITY: ignore case of characters for special values:
98  //      infinity and nan.
99  //  - ALLOW_HEX_FLOATS: allows hexadecimal float literals.
100  //      This *must* start with "0x" and separate the exponent with "p".
101  //      Examples: 0x1.2p3 == 9.0
102  //                0x10.1p0 == 16.0625
103  //      ALLOW_HEX and ALLOW_HEX_FLOATS are indented.
104  //
105  // empty_string_value is returned when an empty string is given as input.
106  // If ALLOW_LEADING_SPACES or ALLOW_TRAILING_SPACES are set, then a string
107  // containing only spaces is converted to the 'empty_string_value', too.
108  //
109  // junk_string_value is returned when
110  //  a) ALLOW_TRAILING_JUNK is not set, and a junk character (a character not
111  //     part of a double-literal) is found.
112  //  b) ALLOW_TRAILING_JUNK is set, but the string does not start with a
113  //     double literal.
114  //
115  // infinity_symbol and nan_symbol are strings that are used to detect
116  // inputs that represent infinity and NaN. They can be null, in which case
117  // they are ignored.
118  // The conversion routine first reads any possible signs. Then it compares the
119  // following character of the input-string with the first character of
120  // the infinity, and nan-symbol. If either matches, the function assumes, that
121  // a match has been found, and expects the following input characters to match
122  // the remaining characters of the special-value symbol.
123  // This means that the following restrictions apply to special-value symbols:
124  //  - they must not start with signs ('+', or '-'),
125  //  - they must not have the same first character.
126  //  - they must not start with digits.
127  //
128  // If the separator character is not kNoSeparator, then that specific
129  // character is ignored when in between two valid digits of the significant.
130  // It is not allowed to appear in the exponent.
131  // It is not allowed to lead or trail the number.
132  // It is not allowed to appear twice next to each other.
133  //
134  // Examples:
135  //  flags = ALLOW_HEX | ALLOW_TRAILING_JUNK,
136  //  empty_string_value = 0.0,
137  //  junk_string_value = NaN,
138  //  infinity_symbol = "infinity",
139  //  nan_symbol = "nan":
140  //    StringToDouble("0x1234") -> 4660.0.
141  //    StringToDouble("0x1234K") -> 4660.0.
142  //    StringToDouble("") -> 0.0  // empty_string_value.
143  //    StringToDouble(" ") -> NaN  // junk_string_value.
144  //    StringToDouble(" 1") -> NaN  // junk_string_value.
145  //    StringToDouble("0x") -> NaN  // junk_string_value.
146  //    StringToDouble("-123.45") -> -123.45.
147  //    StringToDouble("--123.45") -> NaN  // junk_string_value.
148  //    StringToDouble("123e45") -> 123e45.
149  //    StringToDouble("123E45") -> 123e45.
150  //    StringToDouble("123e+45") -> 123e45.
151  //    StringToDouble("123E-45") -> 123e-45.
152  //    StringToDouble("123e") -> 123.0  // trailing junk ignored.
153  //    StringToDouble("123e-") -> 123.0  // trailing junk ignored.
154  //    StringToDouble("+NaN") -> NaN  // NaN string literal.
155  //    StringToDouble("-infinity") -> -inf.  // infinity literal.
156  //    StringToDouble("Infinity") -> NaN  // junk_string_value.
157  //
158  //  flags = ALLOW_OCTAL | ALLOW_LEADING_SPACES,
159  //  empty_string_value = 0.0,
160  //  junk_string_value = NaN,
161  //  infinity_symbol = nullptr,
162  //  nan_symbol = nullptr:
163  //    StringToDouble("0x1234") -> NaN  // junk_string_value.
164  //    StringToDouble("01234") -> 668.0.
165  //    StringToDouble("") -> 0.0  // empty_string_value.
166  //    StringToDouble(" ") -> 0.0  // empty_string_value.
167  //    StringToDouble(" 1") -> 1.0
168  //    StringToDouble("0x") -> NaN  // junk_string_value.
169  //    StringToDouble("0123e45") -> NaN  // junk_string_value.
170  //    StringToDouble("01239E45") -> 1239e45.
171  //    StringToDouble("-infinity") -> NaN  // junk_string_value.
172  //    StringToDouble("NaN") -> NaN  // junk_string_value.
173  //
174  //  flags = NO_FLAGS,
175  //  separator = ' ':
176  //    StringToDouble("1 2 3 4") -> 1234.0
177  //    StringToDouble("1  2") -> NaN // junk_string_value
178  //    StringToDouble("1 000 000.0") -> 1000000.0
179  //    StringToDouble("1.000 000") -> 1.0
180  //    StringToDouble("1.0e1 000") -> NaN // junk_string_value
181  StringToDoubleConverter(int flags,
182                          double empty_string_value,
183                          double junk_string_value,
184                          const char* infinity_symbol,
185                          const char* nan_symbol,
186                          uc16 separator = kNoSeparator)
187      : flags_(flags),
188        empty_string_value_(empty_string_value),
189        junk_string_value_(junk_string_value),
190        infinity_symbol_(infinity_symbol),
191        nan_symbol_(nan_symbol),
192        separator_(separator) {
193  }
194
195  // Performs the conversion.
196  // The output parameter 'processed_characters_count' is set to the number
197  // of characters that have been processed to read the number.
198  // Spaces than are processed with ALLOW_{LEADING|TRAILING}_SPACES are included
199  // in the 'processed_characters_count'. Trailing junk is never included.
200  double StringToDouble(const char* buffer,
201                        int length,
202                        int* processed_characters_count) const;
203
204  // Same as StringToDouble above but for 16 bit characters.
205  double StringToDouble(const uc16* buffer,
206                        int length,
207                        int* processed_characters_count) const;
208
209  // Same as StringToDouble but reads a float.
210  // Note that this is not equivalent to static_cast<float>(StringToDouble(...))
211  // due to potential double-rounding.
212  float StringToFloat(const char* buffer,
213                      int length,
214                      int* processed_characters_count) const;
215
216  // Same as StringToFloat above but for 16 bit characters.
217  float StringToFloat(const uc16* buffer,
218                      int length,
219                      int* processed_characters_count) const;
220
221  // Same as StringToDouble for T = double, and StringToFloat for T = float.
222  template <typename T>
223  T StringTo(const char* buffer,
224             int length,
225             int* processed_characters_count) const;
226
227  // Same as StringTo above but for 16 bit characters.
228  template <typename T>
229  T StringTo(const uc16* buffer,
230             int length,
231             int* processed_characters_count) const;
232
233 private:
234  const int flags_;
235  const double empty_string_value_;
236  const double junk_string_value_;
237  const char* const infinity_symbol_;
238  const char* const nan_symbol_;
239  const uc16 separator_;
240
241  template <class Iterator>
242  double StringToIeee(Iterator start_pointer,
243                      int length,
244                      bool read_as_double,
245                      int* processed_characters_count) const;
246
247  DOUBLE_CONVERSION_DISALLOW_IMPLICIT_CONSTRUCTORS(StringToDoubleConverter);
248};
249
250}  // namespace double_conversion
251
252// ICU PATCH: Close ICU namespace
253U_NAMESPACE_END
254
255#endif  // DOUBLE_CONVERSION_STRING_TO_DOUBLE_H_
256#endif // ICU PATCH: close #if !UCONFIG_NO_FORMATTING
257