generic-library/poco
1
0
Fork 0
mirror of https://github.com/pocoproject/poco.git synced 2025-10-16 18:56:52 +02:00
Code Issues Projects Releases Wiki Activity

added StringTokenizer::find()

Browse Source
This commit is contained in:
Marian Krivos
2012-04-28 09:53:56 +00:00
parent ae48e7465a
commit 9690a4b50f
2 changed files with 595 additions and 437 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
Foundation/include/Poco/StringTokenizer.h
View File

@@ -58,13 +58,14 @@ public:
enum Options enum Options
{ {
TOK_IGNORE_EMPTY = 1, /// ignore empty tokens TOK_IGNORE_EMPTY = 1, /// ignore empty tokens
TOK_TRIM = 2 /// remove leading and trailing whitespace from tokens TOK_TRIM = 2 /// remove leading and trailing whitespace from tokens
}; };
typedef std::vector<std::string>::const_iterator Iterator; typedef std::vector<std::string> TokenVec;
typedef TokenVec::const_iterator Iterator;
StringTokenizer(const std::string& str, const std::string& separators, int options = 0); StringTokenizer(const std::string& str, const std::string& separators, int options = 0);
/// Splits the given string into tokens. The tokens are expected to be /// Splits the given string into tokens. The tokens are expected to be
/// separated by one of the separator characters given in separators. /// separated by one of the separator characters given in separators.
/// Additionally, options can be specified: /// Additionally, options can be specified:
/// * TOK_IGNORE_EMPTY: empty tokens are ignored /// * TOK_IGNORE_EMPTY: empty tokens are ignored
@@ -78,20 +79,40 @@ public:
/// Destroys the tokenizer. /// Destroys the tokenizer.
Iterator begin() const; Iterator begin() const;
Iterator end() const; Iterator end() const;
const std::string& operator [] (std::size_t index) const; const std::string& operator [] (std::size_t index) const;
/// Returns the index'th token. /// Returns const reference the index'th token.
/// Throws a RangeException if the index is out of range. /// Throws a RangeException if the index is out of range.
std::size_t count() const; std::string& operator [] (std::size_t index);
/// Returns the number of tokens. /// Returns reference to the index'th token.
/// Throws a RangeException if the index is out of range.
bool has(const std::string& token) const;
/// Returns true if token exists, false otherwise.
std::size_t find(const std::string& token, std::size_t pos = 0) const;
/// Returns the index of the first occurence of the token
/// starting at position pos.
/// Throws a NotFoundException if the token is not found.
std::size_t replace(const std::string& oldToken, const std::string& newToken, std::size_t pos = 0);
/// Starting at position pos, replaces all subsequent tokens having value
/// equal to oldToken with newToken.
/// Returns the number of modified tokens.
std::size_t count() const;
/// Returns the total number of tokens.
std::size_t count(const std::string& token) const;
/// Returns the number of tokens equal to the specified token.
private: private:
StringTokenizer(const StringTokenizer&); StringTokenizer(const StringTokenizer&);
StringTokenizer& operator = (const StringTokenizer&); StringTokenizer& operator = (const StringTokenizer&);
std::vector<std::string> _tokens; TokenVec _tokens;
}; };
@@ -112,9 +133,16 @@ inline StringTokenizer::Iterator StringTokenizer::end() const
} }
inline std::string& StringTokenizer::operator [] (std::size_t index)
{
if (index >= _tokens.size()) throw RangeException();
return _tokens[index];
}
inline const std::string& StringTokenizer::operator [] (std::size_t index) const inline const std::string& StringTokenizer::operator [] (std::size_t index) const
{ {
if (index >= _tokens.size()) throw RangeException(); if (index >= _tokens.size()) throw RangeException();
return _tokens[index]; return _tokens[index];
} }

410
Foundation/testsuite/src/StringTokenizerTest.cpp
View File

@@ -1,7 +1,7 @@
// //
// StringTokenizerTest.cpp // StringTokenizerTest.cpp
// //
// $Id: //poco/1.4/Foundation/testsuite/src/StringTokenizerTest.cpp#1 $ // $Id: //poco/svn/Foundation/testsuite/src/StringTokenizerTest.cpp#2 $
// //
// Copyright (c) 2004-2006, Applied Informatics Software Engineering GmbH. // Copyright (c) 2004-2006, Applied Informatics Software Engineering GmbH.
// and Contributors. // and Contributors.
@@ -34,9 +34,12 @@
#include "CppUnit/TestCaller.h" #include "CppUnit/TestCaller.h"
#include "CppUnit/TestSuite.h" #include "CppUnit/TestSuite.h"
#include "Poco/StringTokenizer.h" #include "Poco/StringTokenizer.h"
#include "Poco/Exception.h"
using Poco::StringTokenizer; using Poco::StringTokenizer;
using Poco::RangeException;
using Poco::NotFoundException;
StringTokenizerTest::StringTokenizerTest(const std::string& name): CppUnit::TestCase(name) StringTokenizerTest::StringTokenizerTest(const std::string& name): CppUnit::TestCase(name)
@@ -67,146 +70,178 @@ void StringTokenizerTest::testStringTokenizer()
StringTokenizer st("", "", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("", "", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
assert (st.begin() == st.end()); assert (st.begin() == st.end());
} }
{ {
StringTokenizer st("abc", ""); StringTokenizer st("abc", "");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "abc");
assert (it == st.end());
} }
{ {
StringTokenizer st("abc ", "", StringTokenizer::TOK_TRIM); StringTokenizer st("abc ", "", StringTokenizer::TOK_TRIM);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "abc");
assert (it == st.end());
} }
{ {
StringTokenizer st(" abc ", "", StringTokenizer::TOK_TRIM); StringTokenizer st(" abc ", "", StringTokenizer::TOK_TRIM);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "abc");
assert (it == st.end());
} }
{ {
StringTokenizer st(" abc", "", StringTokenizer::TOK_TRIM); StringTokenizer st(" abc", "", StringTokenizer::TOK_TRIM);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "abc");
assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "b"); StringTokenizer st("abc", "b");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (st.find("c") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a");
assert (it != st.end());
assert (*it++ == "c"); assert (*it++ == "c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "b", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc", "b", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (st.find("c") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a");
assert (it != st.end());
assert (*it++ == "c"); assert (*it++ == "c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "bc"); StringTokenizer st("abc", "bc");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (st.find("") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a");
assert (it != st.end());
assert (*it++ == ""); assert (*it++ == "");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM); StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (st.find("") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a");
assert (it != st.end());
assert (*it++ == ""); assert (*it++ == "");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "bc", StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc", "bc", StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "a");
assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "a");
assert (it == st.end());
} }
{ {
StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc", "bc", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (it != st.end());
assert (it == st.end()); assert (*it++ == "a");
assert (it == st.end());
} }
{ {
StringTokenizer st("a a,c c", ","); StringTokenizer st("a a,c c", ",");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a a") == 0);
assert (*it++ == "a a"); assert (st.find("c c") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a a");
assert (it != st.end());
assert (*it++ == "c c"); assert (*it++ == "c c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("a a,c c", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("a a,c c", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a a") == 0);
assert (*it++ == "a a"); assert (st.find("c c") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a a");
assert (it != st.end());
assert (*it++ == "c c"); assert (*it++ == "c c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(" a a , , c c ", ","); StringTokenizer st(" a a , , c c ", ",");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find(" a a ") == 0);
assert (*it++ == " a a "); assert (st.find(" ") == 1);
assert (it != st.end()); assert (st.find(" c c ") == 2);
assert (it != st.end());
assert (*it++ == " a a ");
assert (it != st.end());
assert (*it++ == " "); assert (*it++ == " ");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == " c c "); assert (*it++ == " c c ");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(" a a , , c c ", ",", StringTokenizer::TOK_TRIM); StringTokenizer st(" a a , , c c ", ",", StringTokenizer::TOK_TRIM);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a a") == 0);
assert (*it++ == "a a"); assert (st.find("") == 1);
assert (it != st.end()); assert (st.find("c c") == 2);
assert (it != st.end());
assert (*it++ == "a a");
assert (it != st.end());
assert (*it++ == ""); assert (*it++ == "");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "c c"); assert (*it++ == "c c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(" a a , , c c ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st(" a a , , c c ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a a") == 0);
assert (*it++ == "a a"); assert (st.find("c c") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "a a");
assert (it != st.end());
assert (*it++ == "c c"); assert (*it++ == "c c");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc,def,,ghi , jk, l ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc,def,,ghi , jk, l ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (st.find("def") == 1);
assert (it != st.end()); assert (st.find("ghi") == 2);
assert (st.find("jk") == 3);
assert (st.find("l") == 4);
assert (it != st.end());
assert (*it++ == "abc");
assert (it != st.end());
assert (*it++ == "def"); assert (*it++ == "def");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "ghi"); assert (*it++ == "ghi");
@@ -216,12 +251,17 @@ void StringTokenizerTest::testStringTokenizer()
assert (*it++ == "l"); assert (*it++ == "l");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("abc,def,,ghi // jk, l ", ",/", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("abc,def,,ghi // jk, l ", ",/", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("abc") == 0);
assert (*it++ == "abc"); assert (st.find("def") == 1);
assert (it != st.end()); assert (st.find("ghi") == 2);
assert (st.find("jk") == 3);
assert (st.find("l") == 4);
assert (it != st.end());
assert (*it++ == "abc");
assert (it != st.end());
assert (*it++ == "def"); assert (*it++ == "def");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "ghi"); assert (*it++ == "ghi");
@@ -231,12 +271,18 @@ void StringTokenizerTest::testStringTokenizer()
assert (*it++ == "l"); assert (*it++ == "l");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("a/bc,def,,ghi // jk, l ", ",/", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("a/bc,def,,ghi // jk, l ", ",/", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("a") == 0);
assert (*it++ == "a"); assert (st.find("bc") == 1);
assert (it != st.end()); assert (st.find("def") == 2);
assert (st.find("ghi") == 3);
assert (st.find("jk") == 4);
assert (st.find("l") == 5);
assert (it != st.end());
assert (*it++ == "a");
assert (it != st.end());
assert (*it++ == "bc"); assert (*it++ == "bc");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "def"); assert (*it++ == "def");
@@ -248,42 +294,125 @@ void StringTokenizerTest::testStringTokenizer()
assert (*it++ == "l"); assert (*it++ == "l");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(",ab,cd,", ","); StringTokenizer st(",ab,cd,", ",");
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("") == 0);
assert (*it++ == ""); assert (st.find("ab") == 1);
assert (it != st.end()); assert (st.find("cd") == 2);
assert (it != st.end());
assert (*it++ == "");
assert (it != st.end());
assert (*it++ == "ab"); assert (*it++ == "ab");
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "cd"); assert (*it++ == "cd");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(",ab,cd,", ",", StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st(",ab,cd,", ",", StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("ab") == 0);
assert (*it++ == "ab"); assert (st.find("cd") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "ab");
assert (it != st.end());
assert (*it++ == "cd"); assert (*it++ == "cd");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st(" , ab , cd , ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st(" , ab , cd , ", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
StringTokenizer::Iterator it = st.begin(); StringTokenizer::Iterator it = st.begin();
assert (it != st.end()); assert (st.find("ab") == 0);
assert (*it++ == "ab"); assert (st.find("cd") == 1);
assert (it != st.end()); assert (it != st.end());
assert (*it++ == "ab");
assert (it != st.end());
assert (*it++ == "cd"); assert (*it++ == "cd");
assert (it == st.end()); assert (it == st.end());
} }
{ {
StringTokenizer st("1 : 2 , : 3 ", ":,", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY); StringTokenizer st("1 : 2 , : 3 ", ":,", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
assert (st.count() == 3); assert (st.count() == 3);
assert (st[0] == "1"); assert (st[0] == "1");
assert (st[1] == "2"); assert (st[1] == "2");
assert (st[2] == "3"); assert (st[2] == "3");
} assert (st.find("1") == 0);
assert (st.find("2") == 1);
assert (st.find("3") == 2);
}
}
void StringTokenizerTest::testFind()
{
StringTokenizer st("0,1,2,3,3,2,1,0", ",", StringTokenizer::TOK_TRIM | StringTokenizer::TOK_IGNORE_EMPTY);
assert (st.count() == 8);
assert (2 == st.count("0"));
assert (2 == st.count("1"));
assert (2 == st.count("2"));
assert (2 == st.count("3"));
assert (0 == st.count("4"));
assert (0 == st.count("5"));
assert (0 == st.count("6"));
assert (0 == st.count("7"));
assert (st[0] == "0");
assert (st[1] == "1");
assert (st[2] == "2");
assert (st[3] == "3");
assert (st[4] == "3");
assert (st[5] == "2");
assert (st[6] == "1");
assert (st[7] == "0");
assert (st.has("0"));
assert (st.has("1"));
assert (st.has("2"));
assert (st.has("3"));
assert (!st.has("4"));
assert (!st.has("5"));
assert (!st.has("6"));
assert (!st.has("7"));
assert (st.find("0") == 0);
assert (st.find("1") == 1);
assert (st.find("2") == 2);
assert (st.find("3") == 3);
assert (st.find("0", 1) == 7);
assert (st.find("1", 2) == 6);
assert (st.find("2", 3) == 5);
assert (st.find("3", 4) == 4);
try
{
std::size_t p = st.find("4");
fail ("must fail");
}
catch (NotFoundException&) { }
try
{
std::string s = st[8];
fail ("must fail");
}
catch (RangeException&) { }
st[0] = "1";
st[7] = "1";
assert (st[0] == "1");
assert (st[7] == "1");
assert (0 == st.count("0"));
assert (4 == st.count("1"));
st.replace("2", "5");
assert (0 == st.count("2"));
assert (2 == st.count("5"));
st.replace("3", "6", 4);
assert (1 == st.count("3"));
assert (1 == st.count("6"));
} }
@@ -299,9 +428,10 @@ void StringTokenizerTest::tearDown()
CppUnit::Test* StringTokenizerTest::suite() CppUnit::Test* StringTokenizerTest::suite()
{ {
CppUnit::TestSuite* pSuite = new CppUnit::TestSuite("StringTokenizerTest"); CppUnit::TestSuite* pSuite = new CppUnit::TestSuite("StringTokenizerTest");
CppUnit_addTest(pSuite, StringTokenizerTest, testStringTokenizer); CppUnit_addTest(pSuite, StringTokenizerTest, testStringTokenizer);
CppUnit_addTest(pSuite, StringTokenizerTest, testFind);
return pSuite; return pSuite;
} }