thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-22 15:42:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove useless header file

Browse Source
This commit is contained in:
Alexey Milovidov 2020-08-07 04:07:51 +03:00
parent d1ed1fb83a
commit 1f2d0dce3e
2 changed files with 124 additions and 135 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

125
src/Functions/URL/netloc.cpp
View File

@ -1,10 +1,133 @@
#include <Common/StringUtils/StringUtils.h>
#include <Functions/FunctionFactory.h>
#include <Functions/FunctionStringToString.h>
#include "netloc.h"
#include <Functions/URL/FunctionsURL.h>
namespace DB
{
struct ExtractNetloc
{
/// We use the same as domain function
static size_t getReserveLengthForElement() { return 15; }
static inline StringRef getNetworkLocation(const char * data, size_t size)
{
Pos pos = data;
Pos end = data + size;
/// Skip scheme.
if (pos + 2 < end && pos[0] == '/' && pos[1] == '/')
{
pos += 2;
}
else
{
Pos scheme_end = data + std::min(size, 16UL);
for (++pos; pos < scheme_end; ++pos)
{
if (!isAlphaNumericASCII(*pos))
{
switch (*pos)
{
case '.':
case '-':
case '+':
break;
case ' ': /// restricted symbols
case '\t':
case '<':
case '>':
case '%':
case '{':
case '}':
case '|':
case '\\':
case '^':
case '~':
case '[':
case ']':
case ';':
case '=':
case '&':
return StringRef{};
default:
pos = scheme_end; /// exit from the loop
}
}
}
if (pos + 2 < scheme_end && pos[0] == ':' && pos[1] == '/' && pos[2] == '/')
pos += 3;
else
pos = data;
}
/// Now pos points to the first byte after scheme (if there is).
bool has_identification = false;
Pos question_mark_pos = end;
Pos slash_pos = end;
auto start_of_host = pos;
for (; pos < end; ++pos)
{
switch (*pos)
{
case '/':
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
slash_pos = pos;
break;
case '?':
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
question_mark_pos = pos;
break;
case '#':
return StringRef(start_of_host, pos - start_of_host);
case '@': /// foo:bar@example.ru
has_identification = true;
break;
case ' ': /// restricted symbols in whole URL
case '\t':
case '<':
case '>':
case '%':
case '{':
case '}':
case '|':
case '\\':
case '^':
case '~':
case '[':
case ']':
case ';':
case '=':
case '&':
return pos > start_of_host
? StringRef(start_of_host, std::min(std::min(pos - 1, question_mark_pos), slash_pos) - start_of_host)
: StringRef{};
}
}
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
return StringRef(start_of_host, std::min(std::min(pos, question_mark_pos), slash_pos) - start_of_host);
}
static void execute(Pos data, size_t size, Pos & res_data, size_t & res_size)
{
StringRef host = getNetworkLocation(data, size);
res_data = host.data;
res_size = host.size;
}
};
struct NameNetloc { static constexpr auto name = "netloc"; };
using FunctionNetloc = FunctionStringToString<ExtractSubstringImpl<ExtractNetloc>, NameNetloc>;

134
src/Functions/URL/netloc.h
View File

@ -1,134 +0,0 @@
#pragma once
#include "FunctionsURL.h"
#include <common/find_symbols.h>
#include "protocol.h"
#include <cstring>
#include <Common/StringUtils/StringUtils.h>
namespace DB
{
struct ExtractNetloc
{
/// We use the same as domain function
static size_t getReserveLengthForElement() { return 15; }
static inline StringRef getNetworkLocation(const char * data, size_t size)
{
Pos pos = data;
Pos end = data + size;
/// Skip scheme.
if (pos + 2 < end && pos[0] == '/' && pos[1] == '/')
{
pos += 2;
}
else
{
Pos scheme_end = data + std::min(size, 16UL);
for (++pos; pos < scheme_end; ++pos)
{
if (!isAlphaNumericASCII(*pos))
{
switch (*pos)
{
case '.':
case '-':
case '+':
break;
case ' ': /// restricted symbols
case '\t':
case '<':
case '>':
case '%':
case '{':
case '}':
case '|':
case '\\':
case '^':
case '~':
case '[':
case ']':
case ';':
case '=':
case '&':
return StringRef{};
default:
pos = scheme_end; /// exit from the loop
}
}
}
if (pos + 2 < scheme_end && pos[0] == ':' && pos[1] == '/' && pos[2] == '/')
pos += 3;
else
pos = data;
}
/// Now pos points to the first byte after scheme (if there is).
bool has_identification = false;
Pos question_mark_pos = end;
Pos slash_pos = end;
auto start_of_host = pos;
for (; pos < end; ++pos)
{
switch (*pos)
{
case '/':
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
slash_pos = pos;
break;
case '?':
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
question_mark_pos = pos;
break;
case '#':
return StringRef(start_of_host, pos - start_of_host);
case '@': /// foo:bar@example.ru
has_identification = true;
break;
case ' ': /// restricted symbols in whole URL
case '\t':
case '<':
case '>':
case '%':
case '{':
case '}':
case '|':
case '\\':
case '^':
case '~':
case '[':
case ']':
case ';':
case '=':
case '&':
return pos > start_of_host
? StringRef(start_of_host, std::min(std::min(pos - 1, question_mark_pos), slash_pos) - start_of_host)
: StringRef{};
}
}
if (has_identification)
return StringRef(start_of_host, pos - start_of_host);
else
return StringRef(start_of_host, std::min(std::min(pos, question_mark_pos), slash_pos) - start_of_host);
}
static void execute(Pos data, size_t size, Pos & res_data, size_t & res_size)
{
StringRef host = getNetworkLocation(data, size);
res_data = host.data;
res_size = host.size;
}
};
}