diff options
Diffstat (limited to 'base/string_split.h')
| -rw-r--r-- | base/string_split.h | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/base/string_split.h b/base/string_split.h index 3e7881f..c7cb5e7 100644 --- a/base/string_split.h +++ b/base/string_split.h @@ -4,11 +4,41 @@ #ifndef BASE_STRING_SPLIT_H_ #define BASE_STRING_SPLIT_H_ +#pragma once #include <string> #include <utility> #include <vector> +#include "base/string16.h" + +// TODO(tfarina): Move the following functions into the namespace and update the +// callers. +//----------------------------------------------------------------------------- + +// Splits |str| into a vector of strings delimited by |s|. Append the results +// into |r| as they appear. If several instances of |s| are contiguous, or if +// |str| begins with or ends with |s|, then an empty string is inserted. +// +// Every substring is trimmed of any leading or trailing white space. +// Where wchar_t is char16 (i.e. Windows), |c| must be in BMP +// (Basic Multilingual Plane). Elsewhere (Linux/Mac), wchar_t +// should be a valid Unicode code point (32-bit). +void SplitString(const std::wstring& str, + wchar_t c, + std::vector<std::wstring>* r); +// NOTE: |c| must be in BMP (Basic Multilingual Plane) +void SplitString(const string16& str, + char16 c, + std::vector<string16>* r); +// |str| should not be in a multi-byte encoding like Shift-JIS or GBK in which +// the trailing byte of a multi-byte character can be in the ASCII range. +// UTF-8, and other single/multi-byte ASCII-compatible encodings are OK. +// Note: |c| must be in the ASCII range. +void SplitString(const std::string& str, + char c, + std::vector<std::string>* r); + namespace base { bool SplitStringIntoKeyValues( @@ -22,6 +52,33 @@ bool SplitStringIntoKeyValuePairs( char key_value_pair_delimiter, std::vector<std::pair<std::string, std::string> >* kv_pairs); +// The same as SplitString, but use a substring delimiter instead of a char. +void SplitStringUsingSubstr(const string16& str, + const string16& s, + std::vector<string16>* r); +void SplitStringUsingSubstr(const std::string& str, + const std::string& s, + std::vector<std::string>* r); + +// The same as SplitString, but don't trim white space. +// Where wchar_t is char16 (i.e. Windows), |c| must be in BMP +// (Basic Multilingual Plane). Elsewhere (Linux/Mac), wchar_t +// should be a valid Unicode code point (32-bit). +void SplitStringDontTrim(const std::wstring& str, + wchar_t c, + std::vector<std::wstring>* r); +// NOTE: |c| must be in BMP (Basic Multilingual Plane) +void SplitStringDontTrim(const string16& str, + char16 c, + std::vector<string16>* r); +// |str| should not be in a multi-byte encoding like Shift-JIS or GBK in which +// the trailing byte of a multi-byte character can be in the ASCII range. +// UTF-8, and other single/multi-byte ASCII-compatible encodings are OK. +// Note: |c| must be in the ASCII range. +void SplitStringDontTrim(const std::string& str, + char c, + std::vector<std::string>* r); + } // namespace base #endif // BASE_STRING_SPLIT_H |