From 76b849fbaa276566fa8838d745c0e5fbd2f138bc Mon Sep 17 00:00:00 2001
From: Ralitsa Dardjonova <dardzhonov@uni-sofia.bg>
Date: Wed, 7 Nov 2018 16:01:18 +0200
Subject: First homework - highlighter for python (#17)

* Initial commit

* Fix some typos

	modified:   README

* Delete index.html
---
 homework/81350/py2html/README         |  12 ++
 homework/81350/py2html/Token.cpp      |  39 +++++
 homework/81350/py2html/Token.h        |  52 +++++++
 homework/81350/py2html/build_lexer.sh |   5 +
 homework/81350/py2html/program.py     |  10 ++
 homework/81350/py2html/py2html.cpp    | 258 ++++++++++++++++++++++++++++++++++
 6 files changed, 376 insertions(+)
 create mode 100644 homework/81350/py2html/README
 create mode 100644 homework/81350/py2html/Token.cpp
 create mode 100644 homework/81350/py2html/Token.h
 create mode 100755 homework/81350/py2html/build_lexer.sh
 create mode 100644 homework/81350/py2html/program.py
 create mode 100644 homework/81350/py2html/py2html.cpp

diff --git a/homework/81350/py2html/README b/homework/81350/py2html/README
new file mode 100644
index 0000000..da727c2
--- /dev/null
+++ b/homework/81350/py2html/README
@@ -0,0 +1,12 @@
+To build the program run the bash script build_lexer.sh:
+$ ./build_lexer.sh
+
+To run the highlighter on a given program:
+$ ./py2html <program name>
+When you run the highlighter, it will produce an html
+file in the current directory named "index.html".
+
+There is a test program named program.py:
+$ ./py2html program.py
+
+
diff --git a/homework/81350/py2html/Token.cpp b/homework/81350/py2html/Token.cpp
new file mode 100644
index 0000000..ea17db5
--- /dev/null
+++ b/homework/81350/py2html/Token.cpp
@@ -0,0 +1,39 @@
+#include "Token.h"
+#include<unordered_map>
+
+std::unordered_map<std::string, TokenType> keywords = {
+    {"False", TokenType::False},
+    {"True", TokenType::True},
+    {"None", TokenType::None},
+    {"and", TokenType::And},
+    {"as", TokenType::As},
+    {"assert", TokenType::Assert},
+    {"break", TokenType::Break},
+    {"class", TokenType::Class},
+    {"continue", TokenType::Continue},
+    {"def", TokenType::Def},
+    {"del", TokenType::Del},
+    {"elif", TokenType::Elif},
+    {"else", TokenType::Else},
+    {"except", TokenType::Except},
+    {"finally", TokenType::Finally},
+    {"for", TokenType::For},
+    {"from", TokenType::From},
+    {"global", TokenType::Global},
+    {"if", TokenType::If},
+    {"import", TokenType::Import},
+    {"in", TokenType::In},
+    {"is", TokenType::Is},
+    {"lambda", TokenType::Lambda},
+    {"nonlocal", TokenType::Nonlocal},
+    {"not", TokenType::Not},
+    {"or", TokenType::Or},
+    {"pass", TokenType::Pass},
+    {"print", TokenType::Print},
+    {"raise", TokenType::Raise},
+    {"return", TokenType::Return},
+    {"try", TokenType::Try},
+    {"while", TokenType::While},
+    {"with", TokenType::With},
+    {"yield", TokenType::Yield}
+};
diff --git a/homework/81350/py2html/Token.h b/homework/81350/py2html/Token.h
new file mode 100644
index 0000000..97dda8d
--- /dev/null
+++ b/homework/81350/py2html/Token.h
@@ -0,0 +1,52 @@
+#pragma once
+#include<string>
+#include<unordered_map>
+
+typedef std::string IPLString ;
+
+ enum TokenType{
+    False,
+    None,
+    True,
+    And,
+    As,
+    Assert,
+    Break,
+    Class,
+    Continue,
+    Def,
+    Del,
+    Elif,
+    Else,
+    Except,
+    Finally,
+    For,
+    From,
+    Global,
+    If,
+    Import,
+    In,
+    Is,
+    Lambda,
+    Nonlocal,
+    Not,
+    Or,
+    Pass,
+    Print,
+    Raise,
+    Return,
+    Try,
+    While,
+    With,
+    Yield
+ };
+
+struct Token
+{
+    TokenType Type;
+    unsigned Line;
+    IPLString Lexeme;
+    double Number = 0.0;
+};
+
+extern std::unordered_map<std::string, TokenType> keywords;
diff --git a/homework/81350/py2html/build_lexer.sh b/homework/81350/py2html/build_lexer.sh
new file mode 100755
index 0000000..95492e0
--- /dev/null
+++ b/homework/81350/py2html/build_lexer.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+g++ -Wall -O2 -std=c++11 -c py2html.cpp -o py2html.o
+g++ -Wall -O2 -std=c++11 -c Token.cpp -o Token.o
+g++  -o py2html py2html.o  Token.o  -s
diff --git a/homework/81350/py2html/program.py b/homework/81350/py2html/program.py
new file mode 100644
index 0000000..8343c02
--- /dev/null
+++ b/homework/81350/py2html/program.py
@@ -0,0 +1,10 @@
+num1 = 1.5
+num2 = 6.3
+
+sum = float(num1) + float(num2)
+
+print('The sum of {0} and {1} is {2}'.format(num1, num2, sum))
+
+table = {'Sjoerd': 4127, 'Jack': 4098, 'Dcab': 7678}
+for name, phone in table.items():
+     print(f'{name:10} ==> {phone:10d}')
diff --git a/homework/81350/py2html/py2html.cpp b/homework/81350/py2html/py2html.cpp
new file mode 100644
index 0000000..65d28da
--- /dev/null
+++ b/homework/81350/py2html/py2html.cpp
@@ -0,0 +1,258 @@
+#include <iostream>
+#include <string>
+#include <cctype>
+#include <unistd.h>
+#include <sys/types.h>
+#include <unordered_map>
+#include <set>
+#include "Token.h"
+
+std::string operatorChars = "+-*/%=<>&|^~";
+std::string parenthesisChars = "[]{}(),";
+std::set<std::string> operators = {
+    "+",
+    "-",
+    "*",
+    "/",
+    "//",
+    "%",
+    "**",
+    ">",
+    "<",
+    ">=",
+    "<=",
+    "==",
+    "!=",
+    "&",
+    "|",
+    "~",
+    "^",
+    ">>",
+    "<<",
+    "=",
+    "+=",
+    "-=",
+    "*=",
+    "/=",
+    "%=",
+    "**=",
+    "//=",
+    "^=",
+    "&=",
+    "|=",
+    ">>=",
+    "<<="
+};
+
+using namespace std;
+FILE* in;
+FILE* out;
+
+bool isNumber(char c){
+    return c >= '0' && c <= '9';
+}
+
+bool notValidNumber(char c){
+    return !(isNumber(c) || c == '.');
+}
+
+bool isQuote(char c){
+    return c == '\'' || c == '"';
+}
+
+bool isLastQuote(char firstQuote, char previousChar, char currentChar){
+    return firstQuote == currentChar && previousChar != '\\';
+}
+
+bool isOperator(char c){
+    return operatorChars.find(c) != std::string::npos;
+}
+
+bool isParenthesis(char c){
+    return parenthesisChars.find(c) != std::string::npos;
+}
+
+bool isValidIdentifierChar(char c){
+    return !(isOperator(c) || isParenthesis(c) || isQuote(c) || c == '\n' || isblank(c) || c == ',');
+}
+
+bool isValidOperator(std::string word){
+    std::set<std::string>::iterator iter;
+    iter = operators.find(word);
+    return iter != operators.end();
+}
+
+std::string readFormat(){
+    std::string word = "{";
+    char c;
+
+    while((c = fgetc(in)) != EOF && c != '}'){
+        word += c;
+    }
+    word += '}';
+    return word;
+}
+
+std::string readNumber(){
+    fseek(in, -1, SEEK_CUR);
+    std::string word;
+    char c;
+    int dotCount = 0;
+
+    while((c = fgetc(in)) != EOF && !notValidNumber(c)){
+        //printf("%c", c);
+        if(notValidNumber(c)){
+            return "";
+        } else if(c == '.'){
+            dotCount++;
+            if(dotCount >= 2){
+                return "";
+            }
+        }
+        word += c;
+    }
+    if(notValidNumber(c)){
+        fseek(in, -1, SEEK_CUR);
+    }
+    return word;
+}
+
+std::string readString(char firstQuote){
+    std::string word = "";
+    word += firstQuote;
+    char c;
+    char previousChar = ' ';
+
+    while((c = fgetc(in)) != EOF && !isLastQuote(firstQuote, previousChar, c)){
+        if( c == '{'){
+            fprintf(out, "<span class=\"string\">%s</span>", word.c_str());
+            word = readFormat();
+            fprintf(out, "<span class=\"formatString\">%s</span>", word.c_str());
+            word = "";
+        } else {
+            word += c;
+        }
+        previousChar = c;
+    }
+    word += firstQuote;
+    fprintf(out, "<span class=\"string\">%s</span>", word.c_str());
+    return word;
+}
+
+std::string readOperator(){
+    fseek(in, -1, SEEK_CUR);
+    std::string word;
+    char c;
+    while((c = fgetc(in)) != EOF && isOperator(c)){
+        word += c;
+    }
+    if(!isOperator(c)){
+        fseek(in, -1, SEEK_CUR);
+    }
+    return word;
+}
+
+std::string readWord(){
+    fseek(in, -1, SEEK_CUR);
+    std::string word;
+    char c;
+    while((c = fgetc(in)) != EOF && isValidIdentifierChar(c)){
+        word += c;
+     }
+
+     if(!isValidIdentifierChar(c)){
+        fseek(in, -1, SEEK_CUR);
+     }
+    return word;
+}
+
+void lexer(){
+    char c;
+    bool validSyntaxis = 1;
+    std::string word;
+    std::unordered_map<std::string, TokenType>::const_iterator iter;
+
+    while((c = fgetc(in)) != EOF){
+        if(isQuote(c)){
+            word = readString(c);
+            //fprintf(out, "<span class=\"string\">%s</span>", word.c_str());
+            continue;
+        }
+        if(isNumber(c)){
+            word = readNumber();
+            fprintf(out, "<span class=\"number\">%s</span>", word.c_str());
+            continue;
+        }
+        if(isOperator(c)){
+            word = readOperator();
+            if(isValidOperator(word)){
+                validSyntaxis = 0;
+            }
+            fprintf(out, "<span class=\"operator\">%s</span>", word.c_str());
+            // trqbwa da se proweti dali e korektno
+            // t.e. da e w nqkyw set ili hash
+            continue;
+        }
+        if(isParenthesis(c)){
+            fprintf(out, "%c", c);
+            continue;
+        }
+        if(isblank(c) || c == '\n'){
+            fprintf(out, "%c", c);
+            continue;
+        }
+
+        word = readWord();
+        iter = keywords.find(word);
+        if(iter == keywords.end()){
+            fprintf(out, "%s", word.c_str());
+        } else {
+            fprintf(out, "<span class=\"keyword\">%s</span>", word.c_str());
+        }
+
+    }
+}
+
+int main(int argc, const char* argv[])
+{
+    ++argv, --argc;  /* skip over program name */
+    if ( argc > 0 )
+            in = fopen( argv[0], "r" );
+    else
+            in = stdin;
+
+    out = fopen("index.html", "w");
+
+    fputs(
+        "<!doctype>"
+        "<html>"
+        "<head>"
+        "    <title>program.py</title>"
+        "    <style>"
+        "        .keyword {"
+        "            color: purple;"
+        "        }"
+        "        .number {"
+        "            color: orange;"
+        "        }"
+        "        .string {"
+        "            color: green;"
+        "        }"
+        "        .operator {"
+        "            font-style: bold;"
+        "        }"
+        "        .formatString {"
+        "            color: red;"
+        "        }"
+        "    </style>"
+        "</head>"
+        "<body>"
+        "    <pre class=\"code\">",
+        out);
+
+    lexer();
+    fputs("</pre></body></html>", out);
+    fclose(in);
+    fclose(out);
+    return 0;
+}
-- 
cgit v1.3.1-23-gd82d