mirror of
https://foundry.openuru.org/gitblit/r/CWE-ou-minkata.git
synced 2025-07-19 19:59:09 +00:00
Add string split and tokenize functions
This commit is contained in:
@ -700,6 +700,60 @@ plString plString::ToLower() const
|
|||||||
return str;
|
return str;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static bool ch_in_set(char ch, const char *set)
|
||||||
|
{
|
||||||
|
for (const char *s = set; *s; ++s) {
|
||||||
|
if (ch == *s)
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
|
std::vector<plString> plString::Tokenize(const char *delims)
|
||||||
|
{
|
||||||
|
std::vector<plString> result;
|
||||||
|
|
||||||
|
const char *next = c_str();
|
||||||
|
const char *end = next + GetSize(); // So binary strings work
|
||||||
|
while (next != end) {
|
||||||
|
const char *cur = next;
|
||||||
|
while (cur != end && !ch_in_set(*cur, delims))
|
||||||
|
++cur;
|
||||||
|
|
||||||
|
// Found a delimiter
|
||||||
|
if (cur != next)
|
||||||
|
result.push_back(plString::FromUtf8(next, cur - next));
|
||||||
|
|
||||||
|
next = cur;
|
||||||
|
while (next != end && ch_in_set(*next, delims))
|
||||||
|
++next;
|
||||||
|
}
|
||||||
|
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
|
//TODO: Not binary safe
|
||||||
|
std::vector<plString> plString::Split(const char *split, size_t maxSplits)
|
||||||
|
{
|
||||||
|
std::vector<plString> result;
|
||||||
|
|
||||||
|
const char *next = c_str();
|
||||||
|
size_t splitlen = strlen(split);
|
||||||
|
while (maxSplits > 0) {
|
||||||
|
const char *sp = strstr(next, split);
|
||||||
|
|
||||||
|
if (!sp)
|
||||||
|
break;
|
||||||
|
|
||||||
|
result.push_back(plString::FromUtf8(next, sp - next));
|
||||||
|
next = sp + splitlen;
|
||||||
|
--maxSplits;
|
||||||
|
}
|
||||||
|
|
||||||
|
result.push_back(plString::FromUtf8(next));
|
||||||
|
return result;
|
||||||
|
}
|
||||||
|
|
||||||
plString operator+(const plString &left, const plString &right)
|
plString operator+(const plString &left, const plString &right)
|
||||||
{
|
{
|
||||||
plString cat;
|
plString cat;
|
||||||
|
@ -44,7 +44,7 @@ You can contact Cyan Worlds, Inc. by email legal@cyan.com
|
|||||||
#define plString_Defined
|
#define plString_Defined
|
||||||
|
|
||||||
#include "HeadSpin.h"
|
#include "HeadSpin.h"
|
||||||
#include <stddef.h>
|
#include <vector>
|
||||||
|
|
||||||
typedef unsigned int UniChar;
|
typedef unsigned int UniChar;
|
||||||
|
|
||||||
@ -287,6 +287,13 @@ public:
|
|||||||
plString ToUpper() const;
|
plString ToUpper() const;
|
||||||
plString ToLower() const;
|
plString ToLower() const;
|
||||||
|
|
||||||
|
// Should replace other tokenization methods. The difference between Split
|
||||||
|
// and Tokenize is that Tokenize never returns a blank string (it strips
|
||||||
|
// all delimiters and only returns the pieces left between them), whereas
|
||||||
|
// Split will split on a full string, returning whatever is left between.
|
||||||
|
std::vector<plString> Split(const char *split, size_t maxSplits = kSizeAuto);
|
||||||
|
std::vector<plString> Tokenize(const char *delims = " \t\r\n\f\v");
|
||||||
|
|
||||||
public:
|
public:
|
||||||
struct less
|
struct less
|
||||||
{
|
{
|
||||||
|
Reference in New Issue
Block a user