Move string distance function to utils and format error message

This commit is contained in:
Balajiganapathi S 2017-11-17 21:41:15 +05:30 committed by Alex Beregszaszi
parent 2859834e58
commit b1417b318f
6 changed files with 122 additions and 52 deletions

View File

@ -0,0 +1,77 @@
/*
This file is part of solidity.
solidity is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
solidity is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with solidity. If not, see <http://www.gnu.org/licenses/>.
*/
/** @file StringUtils.h
* @author Balajiganapathi S <balajiganapathi.s@gmail.com>
* @date 2017
*
* String routines
*/
#include "StringUtils.h"
#include <algorithm>
#include <string>
#include <vector>
using namespace std;
using namespace dev;
namespace dev
{
bool stringWithinDistance(string const& _name1, string const& _name2, size_t _maxDistance)
{
if (_name1 == _name2)
return true;
size_t n1 = _name1.size(), n2 = _name2.size();
vector<vector<size_t>> dp(n1 + 1, vector<size_t>(n2 + 1));
// In this dp formulation of DamerauLevenshtein distance we are assuming that the strings are 1-based to make base case storage easier.
// So index accesser to _name1 and _name2 have to be adjusted accordingly
for (size_t i1 = 0; i1 <= n1; ++i1)
{
for (size_t i2 = 0; i2 <= n2; ++i2)
{
if (min(i1, i2) == 0)
// Base case
dp[i1][i2] = max(i1, i2);
else
{
dp[i1][i2] = min(dp[i1 - 1][i2] + 1, dp[i1][i2 - 1] + 1);
// Deletion and insertion
if (_name1[i1 - 1] == _name2[i2 - 1])
// Same chars, can skip
dp[i1][i2] = min(dp[i1][i2], dp[i1 - 1][i2 - 1]);
else
// Different chars so try substitution
dp[i1][i2] = min(dp[i1][i2], dp[i1 - 1][i2 - 1] + 1);
if (i1 > 1 && i2 > 1 && _name1[i1 - 1] == _name2[i2 - 2] && _name1[i1 - 2] == _name2[i2 - 1])
// Try transposing
dp[i1][i2] = min(dp[i1][i2], dp[i1 - 2][i2 - 2] + 1);
}
}
}
size_t distance = dp[n1][n2];
// if distance is not greater than _maxDistance, and distance is strictly less than length of both names,
// they can be considered similar this is to avoid irrelevant suggestions
return distance <= _maxDistance && distance < n1 && distance < n2;
}
}

35
libdevcore/StringUtils.h Normal file
View File

@ -0,0 +1,35 @@
/*
This file is part of solidity.
solidity is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
solidity is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with solidity. If not, see <http://www.gnu.org/licenses/>.
*/
/** @file StringUtils.h
* @author Balajiganapathi S <balajiganapathi.s@gmail.com>
* @date 2017
*
* String routines
*/
#pragma once
#include <string>
namespace dev
{
/// Calculates the DamerauLevenshtein distance between @a _name1 and @a _name2 and
/// @returns true if that distance is not greater than @a _maxDistance
bool stringWithinDistance(std::string const& _name1, std::string const& _name2, size_t _maxDistance);
}

View File

@ -23,6 +23,7 @@
#include <libsolidity/analysis/DeclarationContainer.h>
#include <libsolidity/ast/AST.h>
#include <libsolidity/ast/Types.h>
#include <libdevcore/StringUtils.h>
using namespace std;
using namespace dev;
@ -123,7 +124,7 @@ vector<ASTString> DeclarationContainer::similarNames(ASTString const& _name) con
for (auto const& declaration: m_declarations)
{
string const& declarationName = declaration.first;
if (DeclarationContainer::areSimilarNames(_name, declarationName))
if (stringWithinDistance(_name, declarationName, MAXIMUM_DISTANCE))
similar.push_back(declarationName);
}
@ -135,44 +136,3 @@ vector<ASTString> DeclarationContainer::similarNames(ASTString const& _name) con
return similar;
}
bool DeclarationContainer::areSimilarNames(ASTString const& _name1, ASTString const& _name2)
{
if (_name1 == _name2)
return true;
size_t n1 = _name1.size(), n2 = _name2.size();
vector<vector<size_t>> dp(n1 + 1, vector<size_t>(n2 + 1));
// In this dp formulation of DamerauLevenshtein distance we are assuming that the strings are 1-based to make base case storage easier.
// So index accesser to _name1 and _name2 have to be adjusted accordingly
for (size_t i1 = 0; i1 <= n1; ++i1)
{
for (size_t i2 = 0; i2 <= n2; ++i2)
{
if (min(i1, i2) == 0) // base case
dp[i1][i2] = max(i1, i2);
else
{
dp[i1][i2] = min(dp[i1-1][i2] + 1, dp[i1][i2-1] + 1);
// Deletion and insertion
if (_name1[i1-1] == _name2[i2-1])
// Same chars, can skip
dp[i1][i2] = min(dp[i1][i2], dp[i1-1][i2-1]);
else
// Different chars so try substitution
dp[i1][i2] = min(dp[i1][i2], dp[i1-1][i2-1] + 1);
if (i1 > 1 && i2 > 1 && _name1[i1-1] == _name2[i2-2] && _name1[i1-2] == _name2[i2-1])
// Try transposing
dp[i1][i2] = min(dp[i1][i2], dp[i1-2][i2-2] + 1);
}
}
}
size_t distance = dp[n1][n2];
// If distance is not greater than MAXIMUM_DISTANCE, and distance is strictly less than length of both names,
// they can be considered similar this is to avoid irrelevant suggestions
return distance <= MAXIMUM_DISTANCE && distance < n1 && distance < n2;
}

View File

@ -68,8 +68,6 @@ private:
std::map<ASTString, std::vector<Declaration const*>> m_declarations;
std::map<ASTString, std::vector<Declaration const*>> m_invisibleDeclarations;
// Calculates the DamerauLevenshtein distance and decides whether the two names are similar
static bool areSimilarNames(ASTString const& _name1, ASTString const& _name2);
static size_t const MAXIMUM_DISTANCE = 2;
};

View File

@ -431,13 +431,13 @@ string NameAndTypeResolver::similarNameSuggestions(ASTString const& _name) const
if (suggestions.empty())
return "";
if (suggestions.size() == 1)
return suggestions.front();
return "\"" + suggestions.front() + "\"";
string choices = suggestions.front();
string choices = "\"" + suggestions.front() + "\"";
for (size_t i = 1; i + 1 < suggestions.size(); ++i)
choices += ", " + suggestions[i];
choices += ", \"" + suggestions[i] + "\"";
choices += " or " + suggestions.back();
choices += " or \"" + suggestions.back() + "\"";
return choices;
}

View File

@ -2089,7 +2089,7 @@ BOOST_AUTO_TEST_CASE(similar_name_suggestions_expected)
function g() public { fun(); }
}
)";
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean func?");
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean \"func\"?");
}
BOOST_AUTO_TEST_CASE(no_name_suggestion)
@ -2115,7 +2115,7 @@ BOOST_AUTO_TEST_CASE(multiple_similar_suggestions)
}
}
)";
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean var1, var2, var3, var4 or var5?");
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean \"var1\", \"var2\", \"var3\", \"var4\" or \"var5\"?");
}
BOOST_AUTO_TEST_CASE(multiple_scopes_suggestions)
@ -2129,7 +2129,7 @@ BOOST_AUTO_TEST_CASE(multiple_scopes_suggestions)
}
}
)";
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean log8, log9, log0, log1, log2, log3 or log4?");
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean \"log8\", \"log9\", \"log0\", \"log1\", \"log2\", \"log3\" or \"log4\"?");
}
BOOST_AUTO_TEST_CASE(inheritence_suggestions)
@ -2142,7 +2142,7 @@ BOOST_AUTO_TEST_CASE(inheritence_suggestions)
}
}
)";
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean func?");
CHECK_ERROR(sourceCode, DeclarationError, "Undeclared identifier. Did you mean \"func\"?");
}
BOOST_AUTO_TEST_CASE(no_spurious_suggestions)