post-guard/RubbishBin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add: data-structure-lab & compiler-lab

Browse Source
This commit is contained in:
jackfiled 2024-10-30 17:23:52 +08:00
commit eb8c4fa451
35 changed files with 4266 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
.idea/
cmake-*/
build/

338
GrammarParser/LlParser.cpp Normal file
View File

@ -0,0 +1,338 @@
#include <iostream>
#include <vector>
#include <string>
#include <unordered_map>
#include <unordered_set>
#include <list>
#define EMPTY L'ε'
#define END L'$'
struct Grammar
{
std::unordered_map<wchar_t, std::vector<std::wstring>> Generators;
std::unordered_set<wchar_t> Nonterminators;
wchar_t Begin;
std::unordered_map<wchar_t, std::unordered_set<wchar_t>> FirstSet;
std::unordered_map<wchar_t, std::unordered_set<wchar_t>> FollowSet;
std::unordered_map<wchar_t, std::unordered_map<wchar_t, std::wstring>> AnalysisTable;
Grammar(const std::unordered_map<wchar_t, std::vector<std::wstring>>&generators, const wchar_t begin)
{
Generators = generators;
Begin = begin;
for (const auto&[key, value]: generators)
{
Nonterminators.emplace(key);
FirstSet.emplace(key, std::unordered_set<wchar_t>());
FollowSet.emplace(key, std::unordered_set<wchar_t>());
AnalysisTable.emplace(key, std::unordered_map<wchar_t, std::wstring>());
}
// 求非终结符的FIRST集合
bool changed = true;
while (changed)
{
changed = false;
for (const auto&[key, value]: generators)
{
for (const auto&expression: value)
{
if (Nonterminators.count(expression.front()) != 0)
{
// 合并其他非终结符的FIRST集合
for (const auto&c: FirstSet[expression.front()])
{
if (c != EMPTY and FirstSet[key].count(c) == 0)
{
FirstSet[key].emplace(c);
changed = true;
}
}
}
else
{
if (FirstSet[key].count(expression.front()) == 0)
{
FirstSet[key].emplace(expression.front());
changed = true;
}
}
}
}
}
// 求非终结符的FOLLOW集合
changed = true;
FollowSet[begin].emplace(END);
while (changed)
{
changed = false;
for (const auto&[key, value]: generators)
{
for (const auto&expression: value)
{
for (auto i = expression.begin(); i != expression.end(); ++i)
{
if (Nonterminators.count(*i) != 0)
{
// 发现非终结符
auto next = i;
++next;
if (next == expression.end())
{
// 非终结符在表达式末尾
for (const auto&c: FollowSet[key])
{
if (FollowSet[*i].count(c) == 0)
{
FollowSet[*i].emplace(c);
changed = true;
}
}
continue;
}
std::wstring newExpression;
while (next != expression.end())
{
newExpression += *next;
++next;
}
const auto&firstSet = GetFirstSet(newExpression);
for (const auto&c: firstSet)
{
if (c == EMPTY)
{
for (const auto&j: FollowSet[key])
{
if (FollowSet[*i].count(j) == 0)
{
FollowSet[*i].emplace(j);
changed = true;
}
}
}
else
{
if (FollowSet[*i].count(c) == 0)
{
FollowSet[*i].emplace(c);
changed = true;
}
}
}
}
}
}
}
}
// 生成预测分析表
for (const auto&[key, array]: Generators)
{
for (const auto&expression: array)
{
const auto&firstSet = GetFirstSet(expression);
for (const auto&c: firstSet)
{
if (c == EMPTY)
{
for (const auto&i: FollowSet.at(key))
{
if (!AnalysisTable[key].emplace(i, expression).second)
{
std::cout << "Error, not LL(1) grammar!" << std::endl;
}
}
}
else
{
if (!AnalysisTable[key].emplace(c, expression).second)
{
std::cout << "Error, not LL(1) grammar!" << std::endl;
}
}
}
}
}
}
std::unordered_set<wchar_t> GetFirstSet(const std::wstring&expression) const
{
std::unordered_set<wchar_t> set;
if (Nonterminators.count(expression.front()) != 0)
{
// 起手是非终结符
for (const auto&c: FirstSet.at(expression.front()))
{
// 只有所有的符号都能推出空串 才添加
if (c == EMPTY)
{
bool flag = true;
for (const auto&i: expression)
{
if (Nonterminators.count(i) != 0)
{
flag = FirstSet.at(i).count(EMPTY) != 0;
}
else
{
flag = i == EMPTY;
}
if (!flag)
{
break;
}
}
if (flag)
{
set.emplace(EMPTY);
}
}
else
{
set.emplace(c);
}
}
}
else
{
set.emplace(expression.front());
}
return set;
}
void Analyse(const std::wstring& input, const std::unordered_map<std::wstring, int>& numbers)
{
std::list<wchar_t> states;
auto i = input.begin();
states.emplace_back(END);
states.emplace_back(Begin);
do
{
for (const auto c : states)
{
std::wcout << c;
}
std::wcout << L'\t';
for (auto j = i; j != input.end(); ++j)
{
std::wcout << *j;
}
std::wcout << L'\t';
if (auto top = states.back(); Nonterminators.count(top) != 0)
{
// 栈顶是非终结符
if (AnalysisTable[top].count(*i) == 0)
{
std::wcout << L"error" << std::endl;
break;
}
states.pop_back();
if (AnalysisTable[top][*i].front() != EMPTY)
{
// 如果是空串还是不要加了
for (auto j = AnalysisTable[top][*i].rbegin(); j != AnalysisTable[top][*i].rend(); ++j)
{
states.emplace_back(*j);
}
}
auto expression = top + AnalysisTable[top][*i];
std::wcout << numbers.at(expression);
}
else
{
if (top == *i)
{
if (top == END)
{
std::wcout << L"accept";
}
else
{
std::wcout << L"match";
}
states.pop_back();
++i;
}
else
{
std::wcout << L"error" << std::endl;
break;
}
}
std::wcout << std::endl;
}
while (!states.empty());
}
};
int main()
{
const std::unordered_map<wchar_t, std::vector<std::wstring>> map = {
{'E', {L"TA"}},
{'A', {L"+TA", L"-TA", L"ε"}},
{'T', {L"FB"}},
{'B', {L"ε", L"*FB", L"/FB"}},
{'F', {L"(E)", L"n"}}
};
// 通过另外的表输入产生式编号
const std::unordered_map<std::wstring, int> numbers = {
{L"ETA", 1},
{L"A+TA", 2},
{L"A-TA", 3},
{L"Aε", 4},
{L"TFB", 5},
{L"B*FB", 6},
{L"B/FB", 7},
{L"Bε", 8},
{L"F(E)", 9},
{L"Fn", 10}
};
/**
FIRST
E -> n (
A -> e - +
T -> ( n
B -> / * e
F -> n (
FOLLOW
E -> ) $
A -> $ )
T -> $ ) - +
B -> + - ) $
F -> + - ) $ / *
*/
Grammar grammar(map, 'E');
std::wstring input;
std::wcin >> input;
input += END;
grammar.Analyse(input, numbers);
return 0;
}

443
GrammarParser/LrParser.cpp Normal file
View File

@ -0,0 +1,443 @@
// ReSharper disable CppTooWideScopeInitStatement
// ReSharper disable CppUseStructuredBinding
#include <iostream>
#include <sstream>
#include <memory>
#include <unordered_map>
#include <string>
#include <unordered_set>
#include <algorithm>
#include <vector>
#include <list>
#define END L'$'
struct Expression
{
char Left;
char LookAhead;
std::string Right;
int Pos;
Expression(const char left, const std::string& right, const char lookAhead)
{
Left = left;
LookAhead = lookAhead;
Right = std::string(right);
Pos = 0;
}
std::string GetHashCode() const
{
std::stringstream hash;
hash << Left << Right << Pos << LookAhead;
return hash.str();
}
};
struct ExpressionHash
{
std::size_t operator() (const Expression & expression) const
{
return std::hash<std::string>()(expression.GetHashCode());
}
};
struct ExpressionEqual
{
bool operator() (const Expression& a, const Expression& b) const
{
return a.GetHashCode() == b.GetHashCode();
}
};
struct State
{
std::unordered_set<Expression, ExpressionHash, ExpressionEqual> Expressions;
std::unordered_map<char, std::shared_ptr<State>> Transformers;
explicit State(const std::unordered_set<Expression, ExpressionHash, ExpressionEqual>& expressions)
{
Expressions = expressions;
}
std::string GetHashCode() const
{
std::unordered_map<std::string, std::vector<char>> map;
for (const auto &e : Expressions)
{
std::stringstream stream;
stream << e.Left;
for (size_t i =0 ; i < e.Pos; ++i)
{
stream << e.Right[i];
}
stream << '^';
for (size_t i = e.Pos; i < e.Right.size(); ++i)
{
stream << e.Right[i];
}
const auto expression = stream.str();
if (map.count(expression) == 0)
{
map[expression] = std::vector<char>();
map[expression].emplace_back(e.LookAhead);
}
else
{
map[expression].emplace_back(e.LookAhead);
}
}
std::vector<std::string> list;
for (auto& pair: map)
{
std::string hash(pair.first);
std::sort(pair.second.begin(), pair.second.end());
for (const auto c : pair.second)
{
hash += c;
}
list.emplace_back(hash);
}
std::sort(list.begin(), list.end());
std::string hash;
for (const auto& s : list)
{
hash += s;
}
return hash;
}
};
struct StateHash
{
std::size_t operator() (const std::shared_ptr<State>& s) const
{
return std::hash<std::string>()(s->GetHashCode());
}
};
struct StateEqual
{
bool operator() (const std::shared_ptr<State>& a, const std::shared_ptr<State>& b) const
{
return a->GetHashCode() == b->GetHashCode();
}
};
struct Grammar
{
std::unordered_map<char, std::vector<std::string>> Generators;
char Begin;
std::shared_ptr<State> BeginState;
std::unordered_set<char> Nonterminators;
std::unordered_map<char, std::unordered_set<char>> FirstSet;
std::unordered_set<std::shared_ptr<State>, StateHash, StateEqual> DFA;
Grammar(const std::unordered_map<char, std::vector<std::string>>& map, const char begin)
{
Generators = map;
Begin = begin;
for (const auto& pair : Generators)
{
Nonterminators.emplace(pair.first);
}
// 构造FirstSet
bool changed = true;
while (changed)
{
changed = false;
for (const auto& pair: Generators)
{
for (const auto&expression: pair.second)
{
if (Nonterminators.count(expression.front()) != 0)
{
// 合并其他非终结符的FIRST集合
for (const auto&c: FirstSet[expression.front()])
{
if (FirstSet[pair.first].count(c) == 0)
{
FirstSet[pair.first].emplace(c);
changed = true;
}
}
}
else
{
if (FirstSet[pair.first].count(expression.front()) == 0)
{
FirstSet[pair.first].emplace(expression.front());
changed = true;
}
}
}
}
}
}
~Grammar()
{
DFA.clear();
}
/**
* \brief 计算句子的First集合
* \param expression 需要计算的句子
* \return 句子的First集合
*/
std::unordered_set<char> GetFirstSet(const std::string& expression) const
{
std::unordered_set<char> result;
if (Nonterminators.count(expression.front()) != 0)
{
// 起手是非终结符
for (const char c : FirstSet.at(expression.front()))
{
result.emplace(c);
}
}
else
{
result.emplace(expression.front());
}
return result;
}
std::unordered_set<Expression, ExpressionHash, ExpressionEqual> ConstructClosure(const Expression& expression) const
{
std::unordered_set<Expression, ExpressionHash, ExpressionEqual> result;
result.emplace(expression);
bool changed = true;
while (changed)
{
changed = false;
for (const auto& e : result)
{
const char next = e.Right[e.Pos];
if (Nonterminators.count(next) == 0)
{
continue;
}
std::string ahead;
for (size_t i = e.Pos + 1; i < e.Right.size(); ++i)
{
ahead += e.Right[i];
}
ahead += e.LookAhead;
std::unordered_set<char> lookAheadSet = GetFirstSet(ahead);
for (const auto& i : Generators.at(next))
{
for (const char lookAhead : lookAheadSet)
{
Expression newExpression(next, i, lookAhead);
if (result.count(newExpression) == 0)
{
result.emplace(newExpression);
changed = true;
}
}
}
}
}
return result;
}
void ConstructDFA()
{
const Expression begin = Expression(Begin, Generators.at(Begin).front(), END);
int id = 0;
BeginState = std::make_shared<State>(ConstructClosure(begin));
DFA.emplace(BeginState);
++id;
bool added = true;
while (added)
{
added = false;
for (const auto& state : DFA)
{
// 表示使用key 进行移进可以生成的新LR(1)句型
std::unordered_map<char, std::vector<Expression>> nextExpressions;
for (const auto& e : state->Expressions)
{
Expression nextExpression = Expression(e);
if (nextExpression.Pos >= nextExpression.Right.size())
{
// 移进符号已经到达句型的末尾
continue;
}
nextExpression.Pos++;
if (nextExpressions.count(e.Right[e.Pos]) == 0)
{
std::vector<Expression> list;
list.emplace_back(nextExpression);
nextExpressions.emplace(e.Right[e.Pos], list);
}
else
{
nextExpressions.at(e.Right[e.Pos]).emplace_back(nextExpression);
}
}
for (const auto& pair : nextExpressions)
{
// 针对每个构建项目集闭包
std::unordered_set<Expression, ExpressionHash, ExpressionEqual> closure;
for (const auto& i : pair.second)
{
for (const auto& e : ConstructClosure(i))
{
closure.emplace(e);
}
}
auto nextState = std::make_shared<State>(closure);
auto iter = DFA.find(nextState);
if (iter == DFA.end())
{
// 不存在这个项目集闭包
DFA.emplace(nextState);
state->Transformers.emplace(pair.first, nextState);
++id;
added = true;
}
else
{
// 存在这个项目集闭包
state->Transformers.emplace(pair.first, *iter);
}
}
}
}
}
void Analyse(const std::unordered_map<std::string, int>& numbers, const std::string& input) const
{
std::list<std::shared_ptr<State>> stateStack;
stateStack.emplace_back(BeginState);
std::string buffer(input);
buffer += END;
auto iter = buffer.begin();
while (true)
{
const auto& top = stateStack.back();
// 尝试进行移进
bool acceptFlag = false;
bool reduceFlag = false;
for (const auto& expression : top->Expressions)
{
if (expression.Pos == expression.Right.size() and expression.LookAhead == *iter)
{
if (expression.Left == Begin)
{
acceptFlag = true;
std::cout << "accept" << std::endl;
}
else
{
reduceFlag = true;
std::cout << numbers.at(expression.Left + expression.Right) << std::endl;
for (size_t i = 0; i < expression.Right.size(); ++i)
{
stateStack.pop_back();
}
stateStack.emplace_back(stateStack.back()->Transformers.at(expression.Left));
}
}
}
if (acceptFlag)
{
// 接受
break;
}
if (reduceFlag)
{
// reduce
continue;
}
if (top->Transformers.count(*iter) != 0)
{
stateStack.emplace_back(top->Transformers.at(*iter));
++iter;
std::cout << "shift" << std::endl;
continue;
}
std::cout << "error" << std::endl;
break;
}
}
};
int main()
{
const std::unordered_map<char, std::vector<std::string>> map = {
{'S', {"E"}},
{'E', {"E+T", "E-T", "T"}},
{'T', {"T*F", "T/F", "F"}},
{'F', {"(E)", "n"}}
};
const std::unordered_map<std::string, int> numbers = {
{"SE", 0},
{"EE+T", 1},
{"EE-T", 2},
{"ET", 3},
{"TT*F", 4},
{"TT/F", 5},
{"TF", 6},
{"F(E)", 7},
{"Fn", 8}
};
Grammar grammar(map, 'S');
grammar.ConstructDFA();
std::string input;
std::cin >> input;
grammar.Analyse(numbers, input);
return 0;
}

674
LICENSE Normal file
View File

@ -0,0 +1,674 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program 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.
This program 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 this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<https://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<https://www.gnu.org/licenses/why-not-lgpl.html>.

751
LexicalParser/LexicalParser.cpp Normal file
View File

@ -0,0 +1,751 @@
#include <cstdio>
#include <list>
#include <unordered_map>
#include <unordered_set>
#include <vector>
#include <string>
class LexicalParser
{
public:
int LineCount = 0;
int KeywordCount = 0;
int IdentifierCount = 0;
int OperatorCount = 0;
int DelimiterCount = 0;
int CharCount = 0;
int StringCount = 0;
int NumberCount = 0;
int ErrorCount = 0;
explicit LexicalParser(FILE *file)
{
this->File = file;
}
void Loop()
{
bool mark = false;
while (Readline())
{
while (!Buffer.empty())
{
if (mark)
{
// 多行注释
for (auto i = Buffer.begin(); i != Buffer.end(); i++)
{
if (*i == '*')
{
i++;
if (i != Buffer.end() and *i == '/')
{
mark = false;
i++;
if (i == Buffer.end())
{
Buffer.clear();
}
else
{
Buffer.erase(Buffer.begin(), i);
}
break;
}
}
}
if (mark)
{
// 说明在这行没有找到结束符
Buffer.clear();
continue;
}
// 这行读取完成了
if (Buffer.empty())
{
continue;
}
}
auto pos = Buffer.begin();
if (*pos == '/')
{
pos++;
if (pos != Buffer.end())
{
// 判断单行注释
if (*pos == '/')
{
Buffer.clear();
continue;
}
else if (*pos == '*')
{
mark = true;
pos++;
Buffer.erase(Buffer.begin(), pos);
continue;
}
}
}
if (*Buffer.begin() == ' ' or *Buffer.begin() == '\t')
{
Buffer.pop_front();
continue;
}
// 处理特殊错误 @
if (*Buffer.begin() == '@')
{
Buffer.pop_front();
ErrorCount++;
printf("%d <ERROR,@>\n", LineCount);
continue;
}
if (!Parse())
{
return;
}
}
}
}
private:
std::list<char> Buffer;
FILE *File;
bool Parse()
{
if (ParseCharacter() or ParseString())
{
return true;
}
if (ParseNumber())
{
return true;
}
if (ParseOperator() or ParseDelimiter())
{
return true;
}
if (ParseKeyword())
{
return true;
}
return ParseIdentifier();
}
bool Readline()
{
// 标记是否是最后一行
bool read = false;
while (true)
{
int c = fgetc(File);
if (c == EOF)
{
if (read)
{
LineCount++;
}
return read;
}
else if (c == '\n')
{
LineCount++;
return true;
}
Buffer.emplace_back((char) c);
read = true;
}
}
bool ParseKeyword()
{
auto begin = Buffer.begin();
if (KeywordsMap.count(*begin) != 0)
{
const auto &array = KeywordsMap.at(*begin);
for (const auto &i: array)
{
if (i.length() > Buffer.size())
{
continue;
}
auto pos = Buffer.begin();
bool flag = true;
for (auto c: i)
{
if (c != *pos)
{
flag = false;
break;
}
pos++;
}
if (flag)
{
// 同标识符吻合的字符串
// 如果是标识符，应该是分隔符或者空格
if (pos == Buffer.end() or *pos == ' ' or DelimitersSet.count(*pos) != 0
or OperatorsMap.count(*pos) != 0)
{
KeywordCount++;
std::string output;
for (auto j = Buffer.begin(); j != pos; j++)
{
output += *j;
}
printf("%d <KEYWORD,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
return true;
}
}
}
}
return false;
}
bool ParseIdentifier()
{
auto pos = Buffer.begin();
if (*pos == '_' or (*pos >= 'A' and *pos <= 'Z') or (*pos >= 'a' and *pos <= 'z'))
{
while (*pos == '_' or (*pos >= 'A' and *pos <= 'Z') or (*pos >= 'a' and *pos <= 'z')
or (*pos >= '0' and *pos <= '9'))
{
pos++;
}
if (pos == Buffer.end() or *pos == ' ' or DelimitersSet.count(*pos) != 0
or OperatorsMap.count(*pos) != 0)
{
IdentifierCount++;
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <IDENTIFIER,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
return true;
}
}
return false;
}
bool ParseDelimiter()
{
auto pos = Buffer.begin();
if (DelimitersSet.count(*pos) != 0)
{
DelimiterCount++;
printf("%d <DELIMITER,%c>\n", LineCount, *pos);
Buffer.pop_front();
return true;
}
return false;
}
bool ParseOperator()
{
auto begin = Buffer.begin();
if (OperatorsMap.count(*begin))
{
const auto &array = OperatorsMap.at(*begin);
for (const auto &s: array)
{
if (s.length() > Buffer.size())
{
continue;
}
auto pos = Buffer.begin();
bool flag = true;
for (auto i: s)
{
if (i != *pos)
{
flag = false;
break;
}
pos++;
}
if (flag)
{
OperatorCount++;
// 感觉，，，，
// 可以不用判断运算符的后面是什么
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <OPERATOR,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
return true;
}
}
}
return false;
}
bool ParseCharacter()
{
std::string output;
auto first = Buffer.begin();
auto second = first;
second++;
if (*first == 'L' or *first == 'u' or *first == 'U')
{
if (*second == '\'')
{
output += *first;
Buffer.erase(first, second);
}
}
auto pos = Buffer.begin();
if (*pos == '\'')
{
pos++;
while (true)
{
//处理本行没有闭合的错误
if (pos == Buffer.end())
{
for (auto c: Buffer)
{
output += c;
}
Buffer.clear();
ErrorCount++;
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
return true;
}
if (*pos == '\'')
{
break;
}
if (*pos == '\\')
{
pos++;
}
pos++;
}
pos++;
CharCount++;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <CHARCON,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
return true;
}
return false;
}
bool ParseString()
{
auto first = Buffer.begin();
auto second = first;
second++;
std::string output;
if (*first == 'u' or *first == 'U' or *first == 'L')
{
auto third = second;
third++;
if (*second == '\"')
{
output += *first;
Buffer.erase(first, second);
}
else if (*first == 'u' and *second == '8')
{
if (*third == '\"')
{
output = "u8";
Buffer.erase(first, third);
}
}
}
auto pos = Buffer.begin();
if (*pos == '"')
{
pos++;
while (true)
{
//处理本行没有闭合的错误
if (pos == Buffer.end())
{
for (auto c: Buffer)
{
output += c;
}
Buffer.clear();
ErrorCount++;
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
return true;
}
if (*pos == '"')
{
break;
}
if (*pos == '\\')
{
pos++;
}
pos++;
}
pos++;
StringCount++;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <STRING,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
return true;
}
return false;
}
bool ParseNumber()
{
auto first = Buffer.begin();
auto second = first;
second++;
auto third = second;
third++;
if ((*first >= '0' and *first <= '9') or *first == '.')
{
if (*first == '0' and (*second == 'x' or *second == 'X'))
{
// 处理十六进制数据
ParseHexadecimalNumber();
return true;
}
auto pos = Buffer.begin();
if (*first == '.')
{
// 区分小数点和访问符
if (*second < '0' or *second > '9')
{
return false;
}
pos++;
}
while (pos != Buffer.end() and *pos >= '0' and *pos <= '9' or *pos == '.')
{
pos++;
}
if (pos != Buffer.end() and (*pos == 'e' or *pos == 'E' or *pos == '.'))
{
pos++;
if (*pos == '+' or *pos == '-')
{
pos++;
}
if (pos == Buffer.end() or *pos < '0' or *pos > '9')
{
// 坏了
while (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
pos++;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
ErrorCount++;
Buffer.erase(Buffer.begin(), pos);
return true;
}
}
while (pos != Buffer.end() and *pos >= '0' and *pos <= '9' or *pos == '.')
{
pos++;
}
std::unordered_set<char> suffixSet = {'u', 'l', 'U', 'L', 'f', 'F'};
if (pos != Buffer.end() and suffixSet.count(*pos) != 0)
{
while (pos != Buffer.end() and suffixSet.count(*pos) != 0)
{
pos++;
}
if (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
while (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
pos++;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
ErrorCount++;
Buffer.erase(Buffer.begin(), pos);
return true;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <NUMBER,%s>\n", LineCount, output.c_str());
NumberCount++;
Buffer.erase(Buffer.begin(), pos);
return true;
}
else if (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
while (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
pos++;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
ErrorCount++;
Buffer.erase(Buffer.begin(), pos);
return true;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <NUMBER,%s>\n", LineCount, output.c_str());
NumberCount++;
Buffer.erase(Buffer.begin(), pos);
return true;
}
return false;
}
void ParseHexadecimalNumber()
{
auto pos = Buffer.begin();
pos++;
pos++;
while (true)
{
if ((*pos >= '0' and *pos <= '9') or
(*pos >= 'A' and *pos <= 'F') or
(*pos >= 'a' and *pos <= 'f'))
{
pos++;
}
else if (pos == Buffer.end() or *pos == ' ' or *pos == '\t' or
OperatorsMap.count(*pos) != 0 or
DelimitersSet.count(*pos) != 0)
{
break;
}
else
{
// 遇到错误
while (pos != Buffer.end() and *pos != ' ' and *pos != '\t' and
OperatorsMap.count(*pos) == 0 and
DelimitersSet.count(*pos) == 0)
{
pos++;
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <ERROR,%s>\n", LineCount, output.c_str());
Buffer.erase(Buffer.begin(), pos);
ErrorCount++;
return;
}
}
std::string output;
for (auto i = Buffer.begin(); i != pos; i++)
{
output += *i;
}
printf("%d <NUMBER,%s>\n", LineCount, output.c_str());
NumberCount++;
Buffer.erase(Buffer.begin(), pos);
}
const std::unordered_map<char, std::vector<std::string>> KeywordsMap = {
{'a', {"auto"}},
{'b', {"break"}},
{'c', {"case", "char", "const", "continue"}},
{'d', {"double", "default", "do"}},
{'e', {"else", "extern", "enum"}},
{'f', {"float", "for"}},
{'g', {"goto"}},
{'i', {"if", "int"}},
{'l', {"long"}},
{'s', {"struct", "static", "switch", "short", "signed", "sizeof"}},
{'r', {"register", "return"}},
{'t', {"typedef",}},
{'u', {"union", "unsigned"}},
{'v', {"void", "volatile"}},
{'w', {"while"}}
};
const std::unordered_map<char, std::vector<std::string>> OperatorsMap = {
{'+', {"++", "+=", "+"}},
{'-', {"--", "-=", "->", "-"}},
{'*', {"*=", "*"}},
{'/', {"/=", "/"}},
{'%', {"%=", "%"}},
{'=', {"==", "="}},
{'!', {"!=", "!"}},
{'>', {">>=", ">>", ">=", ">"}},
{'<', {"<<=", "<<", "<=", "<"}},
{'&', {"&&", "&=", "&"}},
{'|', {"||", "|=", "|"}},
{'^', {"^=", "^"}},
{'.', {"."}},
{'~', {"~"}}
};
const std::unordered_set<char> DelimitersSet = {
';', ',', ':', '?', '(', ')', '[', ']', '{', '}'
};
};
int main(int argc, char *argv[])
{
FILE *source_file = fopen(argv[1], "r");
if (source_file == nullptr || argc != 2)
{
printf("Failed to open source File.\n");
}
LexicalParser parser(source_file);
parser.Loop();
printf("%d\n", parser.LineCount);
printf("%d %d %d %d %d %d %d\n", parser.KeywordCount,
parser.IdentifierCount,
parser.OperatorCount,
parser.DelimiterCount,
parser.CharCount,
parser.StringCount,
parser.NumberCount);
printf("%d", parser.ErrorCount);
fclose(source_file);
return 0;
}

27
LexicalParser/pl_start.l Normal file
View File

@ -0,0 +1,27 @@
/* 简单词法分析器 */
/* 功能：能够识别出以小写字母ab结尾的所有字符串（仅含大小写字母）并给打印'Hit!' */
/* 说明：在下面的begin和end之间添加代码，注意格式 */
/* 提示：你只需要保证合法的输入（以ab结尾的字符串）有结果，不合法的输入将会包含在.规则中～ */
%{
#include <stdio.h>
%}
%%
/* begin */
[a-zA-Z]*ab {printf("%s: Hit!\n", yytext);}
/* end */
\n {}
. {}
%%
int yywrap() { return 1; }
int main(int argc, char **argv)
{
if (argc > 1) {
if (!(yyin = fopen(argv[1], "r"))) {
perror(argv[1]);
return 1;
}
}
while (yylex());
return 0;
}

117
LexicalParser/pl_test.l Normal file
View File

@ -0,0 +1,117 @@
/* PL词法分析器 */
/* 功能：能够识别出PL支持的所有单词符号并给出种别值 */
/* 说明：在下面的begin和end之间添加代码，已经实现了标识符和整常量的识别，你需要完成剩下的部分，加油吧！ */
/* 提示：因为是顺序匹配，即从上至下依次匹配规则，所以需要合理安排顺序～ */
%{
#include <stdio.h>
%}
/* begin */
INTCON [\-]?[1-9][0-9]*|0
IDENT [A-Za-z][A-Za-z0-9]*
CHARCON \'[^\']*\'
OFSYM of
ARRAYSYM array
PROGRAMSYM program
MODSYM mod
ANDSYM and
ORSYM or
NOTSYM not
BEGINSYM begin
ENDSYM end
IFSYM if
THENSYM then
ELSESYM else
WHILESYM while
DOSYM do
CALLSYM call
CONSTSYM const
TYPESYM type
VARSYM var
PROCSYM procedure
NEQ \<\>
LEQ \<\=
GEQ \>\=
BECOME \:\=
PLUS \+
MINUS \-
TIMES \*
DIVSYM \/
EQL \=
LSS \<
GTR \>
LBRACK \[
RBRACK \]
LPAREN \(
RPAREN \)
COMMA \,
SEMICOLON \;
PERIOD \.
COLON \:
ERROR [\~\!\@\#\$\%\^\&\_\\]
/* end */
%%
/* begin */
{OFSYM} {printf("%s: OFSYM\n", yytext);}
{ARRAYSYM} {printf("%s: ARRAYSYM\n", yytext);}
{PROGRAMSYM} {printf("%s: PROGRAMSYM\n", yytext);}
{MODSYM} {printf("%s: MODSYM\n", yytext);}
{ANDSYM} {printf("%s: ANDSYM\n", yytext);}
{ORSYM} {printf("%s: ORSYM\n", yytext);}
{NOTSYM} {printf("%s: NOTSYM\n", yytext);}
{BEGINSYM} {printf("%s: BEGINSYM\n", yytext);}
{ENDSYM} {printf("%s: ENDSYM\n", yytext);}
{IFSYM} {printf("%s: IFSYM\n", yytext);}
{THENSYM} {printf("%s: THENSYM\n", yytext);}
{ELSESYM} {printf("%s: ELSESYM\n", yytext);}
{WHILESYM} {printf("%s: WHILESYM\n", yytext);}
{DOSYM} {printf("%s: DOSYM\n", yytext);}
{CALLSYM} {printf("%s: CALLSYM\n", yytext);}
{CONSTSYM} {printf("%s: CONSTSYM\n", yytext);}
{TYPESYM} {printf("%s: TYPESYM\n", yytext);}
{VARSYM} {printf("%s: VARSYM\n", yytext);}
{PROCSYM} {printf("%s: PROCSYM\n", yytext);}
{NEQ} {printf("%s: NEQ\n", yytext);}
{LEQ} {printf("%s: LEQ\n", yytext);}
{GEQ} {printf("%s: GEQ\n", yytext);}
{BECOME} {printf("%s: BECOME\n", yytext);}
{PLUS} {printf("%s: PLUS\n", yytext);}
{MINUS} {printf("%s: MINUS\n", yytext);}
{TIMES} {printf("%s: TIMES\n", yytext);}
{DIVSYM} {printf("%s: DIVSYM\n", yytext);}
{EQL} {printf("%s: EQL\n", yytext);}
{LSS} {printf("%s: LSS\n", yytext);}
{GTR} {printf("%s: GTR\n", yytext);}
{LBRACK} {printf("%s: LBRACK\n", yytext);}
{RBRACK} {printf("%s: RBRACK\n", yytext);}
{LPAREN} {printf("%s: LPAREN\n", yytext);}
{RPAREN} {printf("%s: RPAREN\n", yytext);}
{COMMA} {printf("%s: COMMA\n", yytext);}
{SEMICOLON} {printf("%s: SEMICOLON\n", yytext);}
{PERIOD} {printf("%s: PERIOD\n", yytext);}
{COLON} {printf("%s: COLON\n", yytext);}
{CHARCON} {printf("%s: CHARCON\n", yytext);}
{INTCON} {printf("%s: INTCON\n", yytext);}
{IDENT} {printf("%s: IDENT\n", yytext);}
{ERROR} {printf("%s: ERROR\n", yytext);}
/* end */
\n {}
. {}
%%
int yywrap() { return 1; }
int main(int argc, char **argv)
{
if (argc > 1) {
if (!(yyin = fopen(argv[1], "r"))) {
perror(argv[1]);
return 1;
}
}
while (yylex());
return 0;
}

14
README.md Normal file
View File

@ -0,0 +1,14 @@
# Rubbish Bin
大学四年总有一些时候需要用C++写一些答辩代码。
## 数据结构实验代码
- 实验一：约瑟夫问题`josephus`
- 实验二：迷宫问题`maze`
- 实验三：哈夫曼压缩解压缩搜索`zip-unzip-search`
## 编译原理实验代码
- 实验一：词法分析问题`LexicalParser`
- 实验二：语法分析问题`GrammarParser`

1
josephus/.gitignore vendored Normal file
View File

@ -0,0 +1 @@
.idea/

12
josephus/CMakeLists.txt Normal file
View File

@ -0,0 +1,12 @@
cmake_minimum_required(VERSION 3.16)
set(CMAKE_CXX_STANDARD 11)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall")
project(josephus)
include_directories(${PROJECT_SOURCE_DIR}/include)
aux_source_directory(${PROJECT_SOURCE_DIR}/src SRC)
add_executable(josephus main.cpp ${SRC})

82
josephus/include/LinkedList.h Normal file
View File

@ -0,0 +1,82 @@
//
// Created by ricardo on 9/26/22.
//
#ifndef JOSEPHUS_LINKED_LIST_H
#define JOSEPHUS_LINKED_LIST_H
#include "cstdlib"
#include "cstring"
#include "cstdio"
#include "define.h"
/**
* 列表节点结构体
*/
struct node {
int ID;
char Name[MAX_NAME_LENGTH];
int Age;
int Gender;
struct node* next;
};
typedef struct node node_t;
typedef struct node* node_p;
/**
* 创建循环列表
* @param head 头节点地址的引用
* @return true 创建成功
* @return false 创建失败
*/
bool init_linked_list(node_p& head);
/**
* 销毁链表
* @param head 链表头节点的地址
*/
void destroy_linked_list(node_p& head);
/**
* 创建一个链表中的节点
* @param node 新节点地址引用
* @param id 人的编号
* @param age 人的年龄
* @param gender 人的性别
* @param name 人的姓名字符串
* @return true 创建成功
* @return false 创建失败
*/
bool create_node(node_p& node, int id, int age, int gender, char* name);
/**
* 在链表的末尾插入新节点
* 虽然是循环链表 我们不妨认为头节点前的节点
* @param head 链表头节点的引用
* @param new_node 需要插入的新节点
*/
void append_node(const node_p& head, node_p new_node);
/**
* 从链表中删除指定的节点
* @param head 链表头节点的引用
* @param target_node 需要删除的目标节点
* @return true 删除成功
* @return false 删除失败 一般是目标节点非法
*/
bool delete_node(const node_p& head, node_p target_node);
/**
* 打印指定节点记录人员的信息
* @param node 对指定节点的引用
*/
void print_node(const node_p& node);
/**
* 打印链表中每个节点的值
* @param head 链表头节点的引用
*/
void print_linked_list(const node_p& head);
#endif //JOSEPHUS_LINKED_LIST_H

16
josephus/include/define.h Normal file
View File

@ -0,0 +1,16 @@
//
// Created by ricardo on 2022/9/26.
//
#ifndef JOSEPHUS_DEFINE_H
#define JOSEPHUS_DEFINE_H
// 男性
#define MALE 0
// 女性
#define FEMALE 1
// 姓名字符串的最大长度
#define MAX_NAME_LENGTH 20
#define MAX_GENDER_LENGTH 10
#endif //JOSEPHUS_DEFINE_H

8
josephus/input.txt Normal file
View File

@ -0,0 +1,8 @@
6
1 zyl male 1
2 zzyl male 2
3 zzzyl female 3
4 zyyl female 4
5 zyyyl female 40
6 zyll female 45
0 4 1

135
josephus/main.cpp Normal file
View File

@ -0,0 +1,135 @@
//
// Created by ricardo on 9/26/22.
//
#include "LinkedList.h"
#include "define.h"
node_p read_input()
{
int age, id, gender;
char name[MAX_NAME_LENGTH];
char gender_string[MAX_GENDER_LENGTH];
// 性别字符串
const char* male_string = "male";
const char* female_string = "female";
scanf("%d %s %s %d", &id, name, gender_string, &age);
// 匹配输入的性别字符串
if (strcmp(gender_string, male_string) == 0)
{
gender = MALE;
}
else if (strcmp(gender_string, female_string) == 0)
{
gender = FEMALE;
}
else
{
// 如果匹配失败说明输入非法
return nullptr;
}
node_p node;
if (create_node(node, id, age, gender, name))
{
return node;
}
else
{
return nullptr;
}
}
int main() {
// 存储总共的人数
int number;
// 链表的头节点
node_p head;
if (!init_linked_list(head))
{
// 创建链表的头节点
// 如果创建失败输出错误信息
printf("E: Init linked list failed.\n");
return -1;
}
// 输入人员列表
printf("Hint: Enter number of people join this game:");
scanf("%d", &number);
printf("Hint: Enter the people information list as id name gender(male|female) age.\n");
for (int i = 0; i < number; ++i) {
node_p node = read_input();
if (node == nullptr)
{
printf("E: Create Node failed.\n");
return -1;
}
else
{
append_node(head, node);
}
}
// 打印人员列表
print_linked_list(head);
// 分别记录游戏开始的位置 中间的间隔 最后剩余的人数
int begin, middle, left;
printf("Hint: Enter the begin(begin from 0), middle and left people number.\n");
scanf("%d %d %d", &begin, &middle, &left);
node_p node = head->next;
// 循环到达游戏开始的位置
for (int i = 0; i < begin; ++i) {
node = node->next;
}
// 这里有点屎
// 由于给定的数据是"间隔"
// 在遍历时的次数需要+1
// 但是当前被选中的节点会被删除 在删除之间需要将指针下移一位
// 遍历的次序又需要-1
// 故需要在开始前在指针前移一位
node = node->next;
while (number > left)
{
// 游戏开始
// 由于middle是间隔
for (int i = 0; i < middle; ++i) {
if (node == head)
{
// 由于头节点不存储数据
// 遍历到头节点需要多遍历一次
i--;
}
node = node->next;
}
if (node == head)
{
// 如果恰好在末尾遇到head
// 无法在循环中处理
node = node->next;
}
printf("ID:%d was killed\n", node->ID);
node_p target = node;
node = node->next;
if (!delete_node(head, target))
{
printf("E: delete node failed.\n");
return -1;
}
number--;
}
print_linked_list(head);
// 在退出程序之前 释放链表占用的空间
destroy_linked_list(head);
return 0;
}

132
josephus/src/LinkedList.cpp Normal file
View File

@ -0,0 +1,132 @@
//
// Created by ricardo on 9/26/22.
//
#include "LinkedList.h"
bool init_linked_list(node_p& head)
{
head = (node_p) malloc(sizeof (node_t));
if (head == nullptr)
{
// 空间分配失败
return false;
}
// 由于是创建循环链表 头节点的下一个节点就是头节点
head->next = head;
return true;
}
void destroy_linked_list(node_p& head)
{
node_p node = head->next;
// 先循环处理所有不是头节点的节点
while (node != head)
{
node_p temp = node;
node = node->next;
free(temp);
}
free(head);
head = nullptr;
}
bool create_node(node_p& node, int id, int age, int gender, char* name)
{
node = (node_p) malloc(sizeof(node_t));
if (node == nullptr)
{
// 分配空间失败
return false;
}
node->ID = id;
node->Age = age;
node->Gender = gender;
strcpy(node->Name, name);
return true;
}
void append_node(const node_p& head, node_p new_node)
{
node_p node = head->next;
// 找到头节点前的一个节点
while (node->next != head)
{
node = node->next;
}
node->next = new_node;
new_node->next = head;
}
bool delete_node(const node_p& head, node_p target_node)
{
if (head == target_node)
{
// 删除头节点时不可行的
return false;
}
node_p node = head;
while (node->next != target_node)
{
if (node->next == head)
{
// 循环完了都没找见
// 说明查无此节点
return false;
}
node = node->next;
}
node->next = target_node->next;
free(target_node);
return true;
}
void print_node(const node_p& node)
{
if (node == nullptr)
{
// 指定节点为空
return;
}
printf("ID:%d|", node->ID);
printf("Name:%s|", node->Name);
printf("Age:%d|", node->Age);
if (node->Gender == MALE)
{
printf("Gender:Male\n");
}
else
{
printf("Gender:Female\n");
}
}
void print_linked_list(const node_p& head)
{
if (head == nullptr)
{
// 头节点为空
return;
}
node_p node = head->next;
while (node != head)
{
print_node(node);
node = node->next;
}
}

3
maze/.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
cmake-build-*/
build/
.idea/

10
maze/CMakeLists.txt Normal file
View File

@ -0,0 +1,10 @@
cmake_minimum_required(VERSION 3.16)
project(maze)
set(CMAKE_CXX_STANDARD 11)
include_directories(${PROJECT_SOURCE_DIR}/include)
aux_source_directory(${PROJECT_SOURCE_DIR}/src SRCS)
add_executable(maze main.cpp ${SRCS})

71
maze/include/maze_node.h Normal file
View File

@ -0,0 +1,71 @@
//
// Created by ricardo on 2022/10/25.
//
#ifndef MAZE_MAZE_NODE_H
#define MAZE_MAZE_NODE_H
// 全局的节点总数变量
// 虽然全局变量有点不好
extern int node_number;
struct maze_connect_node
{
// 连接的节点数组索引
int index;
struct maze_connect_node* next;
};
typedef struct maze_connect_node maze_connect_node_t;
typedef struct maze_connect_node* maze_connect_node_p;
struct maze_node
{
// 迷宫中结点的编号
int id;
// 与这个节点相连的节点链表
maze_connect_node_p connect_maze_nodes;
// 当前正在遍历的节点
maze_connect_node_p now_node;
};
// 迷宫节点结构体
typedef struct maze_node maze_node_t;
// 迷宫节点结构体指针
typedef struct maze_node* maze_node_p;
/**
* 创建迷宫节点数组
* @param num 迷宫中节点的数量
* @return 数组地址
*/
maze_node_p create_maze_node_array(int num);
/**
* 在指定的节点中添加与之相连的节点
* @param node 指定的节点引用
* @param target 与之相连的节点
* @return 是否添加成功
*/
bool maze_node_add_connect_node(maze_node_t& node, int target);
/**
* 读取迷宫配置文件
* @param filename 配置文件文件名
* @return 迷宫节点数组地址
*/
maze_node_p read_maze_file(char* filename);
/**
* 打印整个迷宫
* @param node_array 迷宫数组
*/
void print_maze(maze_node_p node_array);
/**
* 释放迷宫节点数组占据的空间
* @param node_array 迷宫节点数组引用
*/
void maze_node_free(maze_node_p& node_array);
#endif //MAZE_MAZE_NODE_H

83
maze/include/stack.h Normal file
View File

@ -0,0 +1,83 @@
//
// Created by ricardo on 2022/10/25.
//
#ifndef MAZE_STACK_H
#define MAZE_STACK_H
#include "cstdlib"
#include "maze_node.h"
// 默认的栈大小
#define DEFAULT_STACK_LENGTH 200
// 由于将迷宫中的所有节点都储存在数组中
// 存储路径的栈就不用存储节点的指针
// 而是直接存储节点在数组中的索引
struct stack {
int* top;
int* base;
int stack_size;
};
typedef struct stack stack_t;
typedef struct stack* stack_p;
/**
* 初始化栈空间
* @param s 栈结构体的引用
* @return 栈是否创建成功
*/
bool init_stack(stack_t& s);
/**
* 判断栈是否为空
* @param s 对于栈结构体的引用
* @return
*/
bool stack_is_empty(const stack_t& s);
/**
* 判断栈是否已满
* @param s 对于结构体的引用
* @return
*/
bool stack_is_full(const stack_t& s);
/**
* 在栈中压入元素
* @param s 栈引用
* @param value 被压入栈的值
* @return 压入栈是否成功
*/
bool stack_push(stack_t& s, int index);
/**
* 在栈中弹出元素
* @param s 栈引用
* @param value 被弹出栈的值
* @return 弹出栈是否成功
*/
bool stack_pop(stack_t& s, int* index);
/**
* 获得栈底的元素
* @param s 栈引用
* @return
*/
int stack_get_bottom(const stack_t& s);
/**
* 获得栈顶的元素
* @param s 栈引用
* @return
*/
int stack_get_top(const stack_t& s);
/**
* 释放栈所占用的空间
* @param s 栈引用
*/
void stack_free(stack_t& s);
#endif //MAZE_STACK_H

76
maze/main.cpp Normal file
View File

@ -0,0 +1,76 @@
#include "maze_node.h"
#include "stack.h"
#include "cstdio"
int main()
{
char config_file[10] = "maze.txt";
maze_node_p node_array = read_maze_file(config_file);
print_maze(node_array);
// 输入迷宫的开始和结束节点
int begin_node, end_node;
printf("Please enter the start node:\n");
scanf("%d", &begin_node);
printf("Please enter the end node:\n");
scanf("%d", &end_node);
// 初始化储存路径的栈
stack_t path_stack;
// 显然栈的最大大小就是迷宫中节点的数量
// 但是由于栈判满的原因需要多一个位置
path_stack.stack_size = node_number + 1;
init_stack(path_stack);
// 初始化将起点填入栈中
stack_push(path_stack, begin_node - 1);
while (stack_get_top(path_stack) + 1 != end_node)
{
maze_connect_node_p& node = node_array[stack_get_top(path_stack)].now_node;
if (node == nullptr)
{
// 节点已经遍历完不抱希望了
// 这个值仅占位
int temp;
stack_pop(path_stack, &temp);
continue;
}
// 遍历栈确定目标节点不在栈中
bool flag = false;
int* p = path_stack.base;
while (p != path_stack.top)
{
if (node->index == *p)
{
flag = true;
break;
}
p++;
}
if (!flag)
{
// 如果在栈中没发现这个节点
stack_push(path_stack, node->index);
}
// 将未探索的节点置为下一个
node = node->next;
}
// 打印路径栈
int* p = path_stack.base;
printf("%d", *p + 1);
p++;
while (p != path_stack.top)
{
printf("->%d", *p + 1);
p++;
}
printf("\n");
stack_free(path_stack);
maze_node_free(node_array);
return 0;
}

20
maze/maze.txt Normal file
View File

@ -0,0 +1,20 @@
17
1-3
2-3
3-5
3-4
3-7
3-8
4-6
7-8
7-11
8-9
8-12
9-13
11-12
12-13
13-14
14-10
13-16
16-15
16-17

110
maze/src/maze_node.cpp Normal file
View File

@ -0,0 +1,110 @@
#include "maze_node.h"
#include "cstdlib"
#include "cstdio"
int node_number;
maze_node_p create_maze_node_array(int num)
{
auto node = (maze_node_p) malloc(num * sizeof(maze_node_t));
maze_node_p p = node;
for (int i = 1; i <= num; ++i) {
p->id = i;
p->connect_maze_nodes = nullptr;
p++;
}
return node;
}
bool maze_node_add_connect_node(maze_node_t& node, int target)
{
auto new_node = (maze_connect_node_p) malloc(sizeof(maze_connect_node_t));
if (new_node == nullptr)
{
// 分配空间失败
return false;
}
new_node->next = nullptr;
new_node->index = target;
if (node.connect_maze_nodes == nullptr)
{
node.connect_maze_nodes = new_node;
// 遍历链表总是从头开始
node.now_node = new_node;
}
else
{
maze_connect_node_p connect_node = node.connect_maze_nodes;
while (connect_node->next != nullptr)
{
// 找到链表末节点
connect_node = connect_node->next;
}
connect_node->next = new_node;
}
return true;
}
maze_node_p read_maze_file(char* filename)
{
FILE* config_file;
char buffer[10];
config_file = fopen(filename, "r");
// 配置文件的第一行要求是迷宫中节点的总数
fgets(buffer, sizeof buffer, config_file);
char* point;
node_number = (int )strtol(buffer, &point, 10);
maze_node_p node_array = create_maze_node_array(node_number);
while (fgets(buffer, sizeof buffer, config_file) != nullptr)
{
int node1, node2;
sscanf(buffer, "%d-%d", &node1, &node2);
// 数组中的索引总是比编号小1
maze_node_add_connect_node(node_array[node1 - 1], node2 - 1);
maze_node_add_connect_node(node_array[node2 - 1], node1 - 1);
}
fclose(config_file);
return node_array;
}
void print_maze(maze_node_p node_array)
{
for (int i = 0; i < node_number; ++i) {
maze_node_t node = node_array[i];
maze_connect_node_p p = node.connect_maze_nodes;
while (p != nullptr)
{
printf("%d->%d\n", node.id, node_array[p->index].id);
p = p->next;
}
}
}
void maze_node_free(maze_node_p& node_array)
{
for(int i = 0; i < node_number; i++)
{
maze_connect_node_p node = node_array[i].connect_maze_nodes;
while (node != nullptr)
{
maze_connect_node_p temp = node;
node = node->next;
free(temp);
}
}
free(node_array);
node_array = nullptr;
}

81
maze/src/stack.cpp Normal file
View File

@ -0,0 +1,81 @@
//
// Created by ricardo on 2022/10/25.
//
#include "stack.h"
bool init_stack(stack_t& s)
{
if (s.stack_size == 0)
{
// 如果没有设置栈的大小
// 就设置为默认大小
s.stack_size = DEFAULT_STACK_LENGTH;
}
auto p = (int* ) malloc(sizeof(int));
if (p == nullptr)
{
// 空间分配失败
return false;
}
s.base = p;
s.top = p;
return true;
}
bool stack_is_empty(const stack& s)
{
return s.base == s.top;
}
bool stack_is_full(const stack& s)
{
return s.base + s.stack_size == s.top;
}
bool stack_push(stack& s,int index)
{
if (stack_is_full(s))
{
// 栈已满
return false;
}
*s.top = index;
s.top++;
return true;
}
bool stack_pop(stack& s, int* index)
{
if (stack_is_empty(s))
{
// 栈为空
return false;
}
*index = *s.top;
s.top--;
return true;
}
int stack_get_bottom(const stack_t& s)
{
return *s.base;
}
int stack_get_top(const stack_t& s)
{
return *(s.top-1);
}
void stack_free(stack_t& s)
{
free(s.base);
s.base = nullptr;
s.top = nullptr;
s.stack_size = 0;
}

3
zip-unzip-search/.gitignore vendored Normal file
View File

@ -0,0 +1,3 @@
.idea/
cmake-*/
build/

10
zip-unzip-search/CMakeLists.txt Normal file
View File

@ -0,0 +1,10 @@
cmake_minimum_required(VERSION 3.22)
project(zip_unzip_search)
set(CMAKE_CXX_STANDARD 11)
include_directories(${PROJECT_SOURCE_DIR}/include)
aux_source_directory(${PROJECT_SOURCE_DIR}/src SRCS)
add_executable(zip_unzip_search main.cpp ${SRCS})

11
zip-unzip-search/include/const.h Normal file
View File

@ -0,0 +1,11 @@
//
// Created by ricardo on 22-12-11.
//
#ifndef ZIP_UNZIP_SEARCH_CONST_H
#define ZIP_UNZIP_SEARCH_CONST_H
// ASCII码的长度
#define ASCII_LENGTH 128
#endif //ZIP_UNZIP_SEARCH_CONST_H

82
zip-unzip-search/include/file_io.h Normal file
View File

@ -0,0 +1,82 @@
//
// Created by ricardo on 22-12-11.
//
#ifndef ZIP_UNZIP_SEARCH_FILE_IO_H
#define ZIP_UNZIP_SEARCH_FILE_IO_H
#include "string"
/**
* 文件元信息
*/
struct MetaData
{
/**
* 哈夫曼树节点数组长度
*/
int HuffmanNodeLength;
/**
* 哈夫曼树根节点长度
*/
int HuffmanRoot;
/**
* 文件中最后一个缓冲区被使用的位数
*/
int LastBufferUsedLength;
};
class FileIO
{
public:
/**
* 统计文件的字符的出现频率
* @param fileName 文件名称
* @return 字符频率数组 需要delete
*/
static int* ReadCharFrequency(const std::string& fileName);
/**
* 写入压缩文件
* @param inputFile 被压缩文件名称
* @param outputFile 输出压缩文件名称
*/
static void WriteZipFile(const std::string& inputFile, const std::string& outputFile);
/**
* 写入解压缩文件
* @param inputFile 压缩文件名称
* @param outputFile 解压文件名称
*/
static void WriteUnzipFile(const std::string& inputFile, const std::string& outputFile);
/**
* 计算文件的压缩率
* @param inputFileName
* @param outputFileName
* @return
*/
static double CalculateZipRate(const std::string& inputFileName, const std::string& outputFileName);
};
class BinaryBuffer
{
public:
explicit BinaryBuffer(std::string& inputFileName);
~BinaryBuffer();
char read();
int position = 0;
private:
FILE* file = nullptr;
int buffer;
int bufferPos;
bool readFinishedFlag;
};
#endif //ZIP_UNZIP_SEARCH_FILE_IO_H

103
zip-unzip-search/include/huffman.h Normal file
View File

@ -0,0 +1,103 @@
//
// Created by ricardo on 22-12-11.
//
#ifndef ZIP_UNZIP_SEARCH_HUFFMAN_H
#define ZIP_UNZIP_SEARCH_HUFFMAN_H
#include "vector"
#include "array"
#include "const.h"
/**
* 哈夫曼树中的节点结构体
*/
struct HuffmanNode
{
/**
* 节点的编号
*/
int id;
/**
* 节点表示的字符
* 如果不是叶子节点
* 值为-1
*/
char data;
/**
* 字符在文件中出现的频率
* 也就是哈夫曼树中节点的权值
*/
int frequency;
/**
* 左子结点在节点数组中的索引
*/
int lIndex;
/**
* 右子结点在节点中的索引
*/
int rIndex;
};
class HuffmanCode
{
public:
/**
* 树中节点列表
*/
std::vector<HuffmanNode>* nodes = new std::vector<HuffmanNode>();
/**
* 哈夫曼树根节点索引
*/
int root = -1;
/**
* 从字符的频率数组出发创建
* @param frequencyArray
*/
explicit HuffmanCode(const int * frequencyArray);
/**
* 从哈夫曼数组节点出发创建
* @param nodeArray 哈夫曼节点数组
* @param length 节点数组的长度
*/
HuffmanCode(HuffmanNode *nodeArray, int length);
~HuffmanCode();
/**
* 创建哈夫曼树
*/
void createHuffmanTree();
/**
* 打印哈夫曼树
*/
void printHuffmanTree();
/**
* 得到哈夫曼编码
* @return 哈夫曼编码字典
*/
std::array<std::vector<char>, ASCII_LENGTH> * getHuffmanCode();
/**
* 打印哈夫曼编码字典
* @param dictionary 字典
*/
static void printHuffmanCode(const std::array<std::vector<char>, ASCII_LENGTH>& dictionary);
private:
/**
* 对森林列表按权值排序
* @param forests
*/
static void sortForests(std::vector<HuffmanNode>& forests);
void printHuffmanTreeR(int nodeId);
void getHuffmanCodeR(std::array<std::vector<char>, ASCII_LENGTH> &dictionary, int nodeId, std::vector<char> &code);
};
#endif //ZIP_UNZIP_SEARCH_HUFFMAN_H

31
zip-unzip-search/include/logging.h Normal file
View File

@ -0,0 +1,31 @@
//
// Created by ricardo on 22-12-11.
//
#ifndef ZIP_UNZIP_SEARCH_LOGGING_H
#define ZIP_UNZIP_SEARCH_LOGGING_H
#include "string"
class Logging
{
public:
/**
* 输出信息
* @param info
*/
static void LoggingInfo(const std::string& info);
/**
* 输出警告
* @param warning
*/
static void LoggingWarning(const std::string& warning);
/**
* 输出错误
* @param error
*/
static void LoggingError(const std::string& error);
};
#endif //ZIP_UNZIP_SEARCH_LOGGING_H

55
zip-unzip-search/include/search.h Normal file
View File

@ -0,0 +1,55 @@
//
// Created by ricardo on 22-12-16.
//
#ifndef ZIP_UNZIP_SEARCH_SEARCH_H
#define ZIP_UNZIP_SEARCH_SEARCH_H
#include "vector"
#include "array"
#include "string"
/**
* BM算法搜索实现类
*/
class BMSearch
{
public:
explicit BMSearch(std::vector<char>& sample);
~BMSearch();
/**
* 匹配二进制文件
* @param fileName 指向需要进行匹配的二进制文件 需要读取元信息和哈夫曼数组
*/
void matchFile(std::string &fileName);
private:
// 坏字符规则数组
// 字符串为01串
int* badCharArray;
// 好后缀规则数组
int* goodSuffixArray;
std::vector<char>* sample;
/**
* 生成坏字符数组
* @param s 模板字符串
*/
void generateBrokenCharArray(std::vector<char>& s);
/**
* 生成好后缀数组
* @param s 模板字符串
*/
void generateGoodSuffixArray(std::vector<char>& s);
static int max(int a, int b);
};
void SearchInFile(char* fileName, char* sample);
#endif //ZIP_UNZIP_SEARCH_SEARCH_H

67
zip-unzip-search/main.cpp Normal file
View File

@ -0,0 +1,67 @@
#include "file_io.h"
#include "logging.h"
#include "cstring"
#include "search.h"
/**
* 输出帮助信息
*/
void PrintHelpMessage()
{
printf("Usage: \n");
printf("Zip File: -z [In-File-Name] [Out-File-Name]\n");
printf("Unzip File: -u [In-File-Name] [Out-File-Name]\n");
printf("Search In Zip File: -s [Zip-File-Name] [Sample-String]\n");
printf("Print Help Message: -h\n");
}
int main(int argc, char *argv[])
{
if (argc == 4)
{
std::string inputFileName = std::string(argv[2]);
std::string outputFileName = std::string(argv[3]);
if (strcmp(argv[1], "-z") == 0)
{
Logging::LoggingInfo("Start Zip File: " + inputFileName + " to zip file: " + outputFileName);
FileIO::WriteZipFile(inputFileName, outputFileName);
double zipRate = FileIO::CalculateZipRate(inputFileName, outputFileName) * 100.0;
Logging::LoggingInfo("The Zip Rate is: " + std::to_string(zipRate) + "%");
Logging::LoggingInfo("Zip Success!");
}
else if(strcmp(argv[1], "-u") == 0)
{
Logging::LoggingInfo("Start Unzip File: " + inputFileName + " to text file: " + outputFileName);
FileIO::WriteUnzipFile(inputFileName, outputFileName);
Logging::LoggingInfo("Unzip Success!");
}
else if(strcmp(argv[1], "-s") == 0)
{
Logging::LoggingInfo("Start to search in file " + inputFileName);
SearchInFile(argv[2], argv[3]);
Logging::LoggingInfo("Search finished");
}
else
{
printf("Unknown Usage!\n");
PrintHelpMessage();
}
}
else if (argc == 2 && strcmp(argv[1], "-h") == 0)
{
PrintHelpMessage();
}
else
{
printf("Unknown Usage!\n");
PrintHelpMessage();
}
return 0;
}

307
zip-unzip-search/src/file_io.cpp Normal file
View File

@ -0,0 +1,307 @@
//
// Created by ricardo on 22-12-11.
//
#include "file_io.h"
#include "logging.h"
#include "cstdio"
#include "cstdlib"
#include "const.h"
#include "huffman.h"
#include "unistd.h"
#include "sys/stat.h"
int *FileIO::ReadCharFrequency(const std::string &fileName)
{
FILE *file = fopen(fileName.c_str(), "r");
if (file == nullptr)
{
// 文件打开失败
Logging::LoggingInfo(fileName + "is not a valid filename");
exit(0);
}
int* frequencyArray = new int[ASCII_LENGTH];
for (int i = 0; i < ASCII_LENGTH; i++)
{
// 将所有频率初始化为0
frequencyArray[i] = 0;
}
while (true)
{
int temp = fgetc(file);
if (temp == EOF)
{
// 文件结束
break;
}
if (temp >= ASCII_LENGTH || temp < 0)
{
// 读取到非法字符
Logging::LoggingWarning(
"Read illegal char " + std::to_string(temp) + " in file. Ignore it");
}
frequencyArray[temp]++;
}
fclose(file);
return frequencyArray;
}
void FileIO::WriteZipFile(const std::string &inputFile, const std::string &outputFile)
{
int* frequencyArray = FileIO::ReadCharFrequency(inputFile);
auto huffmanCode = new HuffmanCode(frequencyArray);
// 创建哈夫曼树
huffmanCode->createHuffmanTree();
auto dictionary = huffmanCode->getHuffmanCode();
FILE* input = fopen(inputFile.c_str(), "r");
FILE* output = fopen(outputFile.c_str(), "wb");
// 判断文件打开ia是否成功
if (input == nullptr)
{
Logging::LoggingError(inputFile + " is not an valid file name.");
exit(0);
}
if (output == nullptr)
{
Logging::LoggingError(outputFile + " is not an valid file name.");
exit(0);
}
// 首先写入文件的元信息
// 虽然目前元信息中部分信息还没有拿到
// 但是先把文件中的空间占据了再说
MetaData metaDataT{};
fwrite(&metaDataT, sizeof(MetaData), 1, output);
// 写入哈夫曼数组
fwrite(huffmanCode->nodes->data(), sizeof(HuffmanNode), huffmanCode->nodes->size(), output);
// 写入文件时的缓冲区
int buffer = 0;
int bufferPos = 0;
while (true)
{
int temp = fgetc(input);
// 读取到文件末尾
if (temp == EOF)
{
buffer = buffer << (32 - bufferPos);
fwrite(&buffer, sizeof(int), 1, output);
metaDataT.LastBufferUsedLength = bufferPos;
break;
}
if (temp >= ASCII_LENGTH || temp < 0)
{
// 读取到非法字符
Logging::LoggingWarning(
"Read illegal char " + std::to_string(temp) + " in file. Ignore it");
}
auto code = (*dictionary)[temp];
for (auto iter = code.begin(); iter < code.end(); iter++)
{
// 缓冲区已经满了
if (bufferPos == 32)
{
fwrite(&buffer, sizeof(int), 1, output);
bufferPos = 0;
buffer = 0;
}
buffer = (buffer << 1) + *iter;
bufferPos++;
}
}
metaDataT.HuffmanRoot = huffmanCode->root;
metaDataT.HuffmanNodeLength = (int )huffmanCode->nodes->size();
// 写入元信息
fseek(output, 0, SEEK_SET);
fwrite(&metaDataT, sizeof(MetaData), 1, output);
delete frequencyArray;
delete huffmanCode;
delete dictionary;
}
void FileIO::WriteUnzipFile(const std::string &inputFile, const std::string &outputFile)
{
FILE* input = fopen(inputFile.c_str(), "rb");
FILE* output = fopen(outputFile.c_str(), "w");
// 检查文件是否正常打开
if (input == nullptr)
{
Logging::LoggingError(inputFile + " is not a valid file name.");
exit(0);
}
if (output == nullptr)
{
Logging::LoggingError(outputFile + " is not a valid file name.");
exit(0);
}
// 读取元信息
MetaData metaData{};
fread(&metaData, sizeof(MetaData), 1, input);
// 读取哈夫曼节点数组
auto nodes = new HuffmanNode[metaData.HuffmanNodeLength];
fread(nodes, sizeof(HuffmanNode), metaData.HuffmanNodeLength, input);
// 读取文件的缓冲区
int buffer;
fread(&buffer, sizeof(int), 1, input);
int bufferPos;
int nextBuffer;
HuffmanNode node = nodes[metaData.HuffmanRoot];
while (true)
{
if (buffer == EOF)
{
// 读取结束
break;
}
// 这里为了处理最后一个缓冲区的问题
// 设置了双缓冲
size_t readResult = fread(&nextBuffer, sizeof(int), 1, input);
if (readResult != 1)
{
// 读取到文件末尾
nextBuffer = EOF;
bufferPos = metaData.LastBufferUsedLength;
}
else
{
bufferPos = 32;
}
while (bufferPos > 0)
{
if (node.data == -1)
{
// 非叶子节点
int value = (buffer >> 31) & 1;
buffer = buffer << 1;
bufferPos--;
if (value == 0)
{
node = nodes[node.lIndex];
}
else
{
node = nodes[node.rIndex];
}
}
else
{
// 叶子节点
fputc(node.data, output);
node = nodes[metaData.HuffmanRoot];
}
}
buffer = nextBuffer;
}
delete[] nodes;
fclose(input);
fclose(output);
}
double FileIO::CalculateZipRate(const std::string &inputFileName, const std::string &outputFileName)
{
struct stat originFileStat{};
struct stat zipFileStat{};
stat(inputFileName.c_str(), &originFileStat);
stat(outputFileName.c_str(), &zipFileStat);
auto originFileSize = (double )originFileStat.st_size;
auto zipFileSize = (double )zipFileStat.st_size;
return zipFileSize / originFileSize;
}
BinaryBuffer::BinaryBuffer(std::string &inputFileName)
{
file = fopen(inputFileName.c_str(), "rb");
if (file == nullptr)
{
// 读取文件失败
Logging::LoggingError(inputFileName + " is not a valid file name.");
exit(0);
}
buffer = 0;
bufferPos = 0;
readFinishedFlag = false;
// 读取文件开头的元信息和哈夫曼数组
MetaData metaData{};
fread(&metaData, sizeof(MetaData), 1, file);
position = position + (int )sizeof(MetaData) * 8;
// 读取哈夫曼节点数组
HuffmanNode nodes[metaData.HuffmanNodeLength];
fread(nodes, sizeof(HuffmanNode), metaData.HuffmanNodeLength, file);
position = position + (int )sizeof(HuffmanNode) * metaData.HuffmanNodeLength * 8;
}
BinaryBuffer::~BinaryBuffer()
{
fclose(file);
file = nullptr;
}
char BinaryBuffer::read()
{
if (readFinishedFlag)
{
return -1;
}
if (bufferPos == 0)
{
// 当前缓冲区读取结束
int result = (int )fread(&buffer, sizeof(int), 1, file);
if (result == 0)
{
readFinishedFlag = true;
// 文件读取结束
return -1;
}
bufferPos = 32;
}
int result = (buffer >> 31) & 1;
buffer = buffer << 1;
bufferPos--;
position++;
return (char )result;
}

176
zip-unzip-search/src/huffman.cpp Normal file
View File

@ -0,0 +1,176 @@
//
// Created by ricardo on 22-12-11.
//
#include "huffman.h"
#include "const.h"
#include "cstdio"
HuffmanCode::HuffmanCode(const int *frequencyArray)
{
for (int i = 0; i < ASCII_LENGTH; i++)
{
HuffmanNode node{};
node.data = (char )i;
node.frequency = frequencyArray[i];
node.id = i;
node.lIndex = -1;
node.rIndex = -1;
nodes->push_back(node);
}
}
HuffmanCode::HuffmanCode(HuffmanNode *nodeArray, int length)
{
delete nodes;
nodes = new std::vector<HuffmanNode>(nodeArray, nodeArray + length);
}
HuffmanCode::~HuffmanCode()
{
delete nodes;
}
void HuffmanCode::sortForests(std::vector<HuffmanNode> &forests)
{
std::size_t length = forests.size();
bool sorted = false;
for (std::size_t i = 1; i < length and !sorted; i++)
{
sorted = true;
for (std::size_t j = 0; j < length - i; j++)
{
if (forests[j].frequency > forests[j + 1].frequency)
{
HuffmanNode node = forests[j];
forests[j] = forests[j + 1];
forests[j + 1] = node;
sorted = false;
}
}
}
}
void HuffmanCode::createHuffmanTree()
{
auto forests = new std::vector<HuffmanNode>(*nodes);
// 节点数组里的编号
int pos = (*nodes).rbegin()->id + 1;
while (forests->size() != 1)
{
// 反复执行建树的过程
sortForests(*forests);
HuffmanNode node{};
node.frequency = (*forests)[0].frequency + (*forests)[1].frequency;
node.data = -1;
// 权值大的节点为左子结点
// 权值小的节点为右子结点
node.rIndex = (*forests)[0].id;
node.lIndex = (*forests)[1].id;
node.id = pos;
pos++;
nodes->push_back(node);
// 在森里中删除已经合并的两棵树
// 新建一颗树
forests->erase(forests->begin(), forests->begin() + 2);
forests->push_back(node);
}
root = forests->begin()->id;
delete forests;
}
void HuffmanCode::printHuffmanTree()
{
if (root == -1)
{
return;
}
printHuffmanTreeR(root);
}
void HuffmanCode::printHuffmanTreeR(int nodeId)
{
HuffmanNode node = (*nodes)[nodeId];
// 不打印权值为0的节点
if (node.lIndex != -1 and node.frequency != 0)
{
printf("%d %d\n", node.id, node.lIndex);
printHuffmanTreeR(node.lIndex);
}
if (node.rIndex != -1 and node.frequency != 0)
{
printf("%d %d\n", node.id, node.rIndex);
printHuffmanTreeR(node.rIndex);
}
}
std::array<std::vector<char>, 128> * HuffmanCode::getHuffmanCode()
{
if (root == -1)
{
return nullptr;
}
auto dictionary = new std::array<std::vector<char>, ASCII_LENGTH>();
std::vector<char> code;
getHuffmanCodeR(*dictionary, root, code);
return dictionary;
}
void HuffmanCode::getHuffmanCodeR(std::array<std::vector<char>, ASCII_LENGTH> &dictionary, int nodeId,
std::vector<char> &code)
{
HuffmanNode node = (*nodes)[nodeId];
if (node.data != -1)
{
for (auto iterator = code.begin(); iterator < code.end(); iterator++)
{
dictionary[node.data].push_back(*iterator);
}
}
if (node.lIndex != -1)
{
// 遍历左子树
code.push_back(0);
getHuffmanCodeR(dictionary, node.lIndex, code);
code.pop_back();
}
if (node.rIndex != -1)
{
// 遍历右子树
code.push_back(1);
getHuffmanCodeR(dictionary, node.rIndex, code);
code.pop_back();
}
}
void HuffmanCode::printHuffmanCode(const std::array<std::vector<char>, ASCII_LENGTH>& dictionary)
{
for (int i = 0; i < ASCII_LENGTH; i++)
{
auto code = dictionary[i];
printf("%d: ", i);
for (auto iter = code.begin(); iter < code.end(); iter++)
{
putc(*iter + 48, stdout);
}
putc('\n', stdout);
}
}

20
zip-unzip-search/src/logging.cpp Normal file
View File

@ -0,0 +1,20 @@
//
// Created by ricardo on 22-12-11.
//
#include "logging.h"
#include "cstdio"
void Logging::LoggingInfo(const std::string &info)
{
printf("[Info] %s\n", info.c_str());
}
void Logging::LoggingWarning(const std::string &warning)
{
printf("[warning] %s\n", warning.c_str());
}
void Logging::LoggingError(const std::string &error)
{
printf("[error] %s\n", error.c_str());
}

194
zip-unzip-search/src/search.cpp Normal file
View File

@ -0,0 +1,194 @@
//
// Created by ricardo on 22-12-16.
//
#include "search.h"
#include "cstdio"
#include "cstring"
#include "logging.h"
#include "file_io.h"
#include "huffman.h"
BMSearch::BMSearch(std::vector<char> &sample)
{
int length = (int )sample.size();
badCharArray = new int[2];
goodSuffixArray = new int[length];
this->sample = new std::vector<char>(sample);
generateBrokenCharArray(sample);
generateGoodSuffixArray(sample);
}
BMSearch::~BMSearch()
{
delete badCharArray;
delete goodSuffixArray;
}
void BMSearch::generateBrokenCharArray(std::vector<char> &s)
{
int length = (int )s.size();
// 输入字符串为01串
for (int i = 0; i < 2; i++)
{
badCharArray[i] = length;
}
for (int i = 0; i < length - 1; i++)
{
badCharArray[s[i]] = length - i - 1;
}
}
void BMSearch::generateGoodSuffixArray(std::vector<char> &s)
{
int length = (int )s.size();
int suffix[length];
suffix[length - 1] = length;
for (int i = length - 2; i >= 0; i--)
{
int pos = i;
while (pos >= 0 and s[pos] == s[length - 1 - i + pos])
{
pos--;
}
suffix[i] = i - pos;
}
for (int i = 0; i < length; i++)
{
goodSuffixArray[i] = length;
}
int j = 0;
for (int i = length - 1; i >= 0 ; i--)
{
if (suffix[i] == i + 1)
{
for (; j < length - 1 - i; j++)
{
if (goodSuffixArray[j] == length)
{
goodSuffixArray[j] = length - 1 - i;
}
}
}
}
for (int i = 0; i < length - 1; i++)
{
goodSuffixArray[length - 1 - suffix[i]] = length - 1 - i;
}
}
void BMSearch::matchFile(std::string &fileName)
{
auto buffer = new BinaryBuffer(fileName);
std::vector<char> inputArray;
while (true)
{
if (inputArray.size() != sample->size())
{
// bm算法要求后缀匹配
// 所以开始之间需要读取一个长度和模式字符串长度相同的缓冲区
char temp = buffer->read();
if (temp == -1)
{
break;
}
else
{
inputArray.push_back(temp);
continue;
}
}
else
{
// 正式开始匹配
int pos = (int )sample->size() - 1;
for(; pos >= 0 and (*sample)[pos] == inputArray[pos]; pos--);
if (pos < 0)
{
// 完成一次匹配
Logging::LoggingInfo("Found at " + std::to_string(buffer->position));
auto begin = inputArray.begin();
auto end = begin + goodSuffixArray[0];
inputArray.erase(begin, end);
}
else
{
// 匹配失败
auto begin = inputArray.begin();
int teleport = max(goodSuffixArray[pos],
badCharArray[inputArray[pos]] - (int )sample->size() + 1 + pos);
auto end = begin + teleport;
inputArray.erase(begin, end);
}
}
}
delete buffer;
}
int BMSearch::max(int a, int b)
{
return a >= b ? a : b;
}
void SearchInFile(char* fileName, char* sample)
{
FILE* file = fopen(fileName, "rb");
if (file == nullptr)
{
Logging::LoggingError(std::string(fileName) + " is not a valid file name.");
exit(0);
}
// 读取元信息
MetaData metaData{};
fread(&metaData, sizeof(MetaData), 1, file);
// 读取哈夫曼节点数组
auto nodes = new HuffmanNode[metaData.HuffmanNodeLength];
fread(nodes, sizeof(HuffmanNode), metaData.HuffmanNodeLength, file);
fclose(file);
// 从哈夫曼节点数组创建哈夫曼编码
auto huffmanCode = new HuffmanCode(nodes, metaData.HuffmanNodeLength);
huffmanCode->root = metaData.HuffmanRoot;
auto dictionary = huffmanCode->getHuffmanCode();
// 获得模板字符串的哈夫曼编码
std::vector<char> sampleCode;
int sampleLength = (int )strlen(sample);
Logging::LoggingInfo("The binary representation of " + std::string(sample) + " is ");
for (int i = 0; i < sampleLength; i++)
{
auto code = (*dictionary)[sample[i]];
for (auto iter = code.begin(); iter < code.end(); iter++)
{
sampleCode.push_back(*iter);
putc(*iter + 48, stdout);
}
}
putc('\n', stdout);
// 开始查找
auto bm = new BMSearch(sampleCode);
std::string str = std::string(fileName);
bm->matchFile(str);
delete bm;
delete[] nodes;
delete huffmanCode;
delete dictionary;
}