docs: add pSet7/similarities

Author: emiliegervais

README.md

@@ -24,7 +24,8 @@ This repository contains my solutions to each problem sets:
     - [Cash](./pSet6/cash/)
     - [Caesar](./pSet6/caesar/)
     - [Bleep](./pSet6/bleep/)
-- pSet7 → 
-- pSet8 → 
+- pSet7 → Flask & AJAX
+    - [Similarities](./pSet7/similarities)
+- pSet8 → SQL
 - **Week 9 is off**
 - pSet10 → 

pSet7/similarities/application.py

@@ -0,0 +1,141 @@
+import cs50
+import re
+from flask import Flask, abort, redirect, render_template, request
+from html import escape
+from werkzeug.exceptions import default_exceptions, HTTPException
+
+from helpers import lines, sentences, substrings
+
+# Configure application
+app = Flask(__name__)
+
+# Reload templates when they are changed
+app.config["TEMPLATES_AUTO_RELOAD"] = True
+
+
+@app.after_request
+def after_request(response):
+    """Disable caching"""
+    response.headers["Cache-Control"] = "no-cache, no-store, must-revalidate"
+    response.headers["Expires"] = 0
+    response.headers["Pragma"] = "no-cache"
+    return response
+
+
+@app.route("/")
+def index():
+    """Handle requests for / via GET (and POST)"""
+    return render_template("index.html")
+
+
+@app.route("/compare", methods=["POST"])
+def compare():
+    """Handle requests for /compare via POST"""
+
+    # Read files
+    if not request.files["file1"] or not request.files["file2"]:
+        abort(400, "missing file")
+    try:
+        file1 = request.files["file1"].read().decode("utf-8")
+        file2 = request.files["file2"].read().decode("utf-8")
+    except Exception:
+        abort(400, "invalid file")
+
+    # Compare files
+    if not request.form.get("algorithm"):
+        abort(400, "missing algorithm")
+    elif request.form.get("algorithm") == "lines":
+        regexes = [f"^{re.escape(match)}$" for match in lines(file1, file2)]
+    elif request.form.get("algorithm") == "sentences":
+        regexes = [re.escape(match) for match in sentences(file1, file2)]
+    elif request.form.get("algorithm") == "substrings":
+        if not request.form.get("length"):
+            abort(400, "missing length")
+        elif not int(request.form.get("length")) > 0:
+            abort(400, "invalid length")
+        regexes = [re.escape(match) for match in substrings(
+            file1, file2, int(request.form.get("length")))]
+    else:
+        abort(400, "invalid algorithm")
+
+    # Highlight files
+    highlights1 = highlight(file1, regexes)
+    highlights2 = highlight(file2, regexes)
+
+    # Output comparison
+    return render_template("compare.html", file1=highlights1, file2=highlights2)
+
+
+def highlight(s, regexes):
+    """Highlight all instances of regexes in s."""
+
+    # Get intervals for which strings match
+    intervals = []
+    for regex in regexes:
+        if not regex:
+            continue
+        matches = re.finditer(regex, s, re.MULTILINE)
+        for match in matches:
+            intervals.append((match.start(), match.end()))
+    intervals.sort(key=lambda x: x[0])
+
+    # Combine intervals to get highlighted areas
+    highlights = []
+    for interval in intervals:
+        if not highlights:
+            highlights.append(interval)
+            continue
+        last = highlights[-1]
+
+        # If intervals overlap, then merge them
+        if interval[0] <= last[1]:
+            new_interval = (last[0], interval[1])
+            highlights[-1] = new_interval
+
+        # Else, start a new highlight
+        else:
+            highlights.append(interval)
+
+    # Maintain list of regions: each is a start index, end index, highlight
+    regions = []
+
+    # If no highlights at all, then keep nothing highlighted
+    if not highlights:
+        regions = [(0, len(s), False)]
+
+    # If first region is not highlighted, designate it as such
+    elif highlights[0][0] != 0:
+        regions = [(0, highlights[0][0], False)]
+
+    # Loop through all highlights and add regions
+    for start, end in highlights:
+        if start != 0:
+            prev_end = regions[-1][1]
+            if start != prev_end:
+                regions.append((prev_end, start, False))
+        regions.append((start, end, True))
+
+    # Add final unhighlighted region if necessary
+    if regions[-1][1] != len(s):
+        regions.append((regions[-1][1], len(s), False))
+
+    # Combine regions into final result
+    result = ""
+    for start, end, highlighted in regions:
+        escaped = escape(s[start:end])
+        if highlighted:
+            result += f"<span>{escaped}</span>"
+        else:
+            result += escaped
+    return result
+
+
+@app.errorhandler(HTTPException)
+def errorhandler(error):
+    """Handle errors"""
+    return render_template("error.html", error=error), error.code
+
+
+# https://github.com/pallets/flask/pull/2314
+for code in default_exceptions:
+    app.errorhandler(code)(errorhandler)

pSet7/similarities/compare

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+
+import argparse
+import re
+import sys
+
+from helpers import lines, sentences, substrings
+
+
+def main():
+
+    # Parse command-line arguments
+    parser = argparse.ArgumentParser()
+    group = parser.add_mutually_exclusive_group(required=True)
+    group.add_argument("--lines", action="store_true", help="compare lines")
+    group.add_argument("--sentences", action="store_true", help="compare sentences")
+    group.add_argument("--substrings", metavar="N", type=positive,
+                       help="compare substrings of length N")
+    parser.add_argument("FILE1", help="file to compare")
+    parser.add_argument("FILE2", help="file to compare")
+    args = vars(parser.parse_args())
+
+    # Read files
+    try:
+        with open(args["FILE1"], "r") as file:
+            file1 = file.read()
+    except IOError:
+        sys.exit(f"Could not read {args['FILE1']}")
+    try:
+        with open(args["FILE2"], "r") as file:
+            file2 = file.read()
+    except IOError:
+        sys.exit(f"Could not read {args['FILE2']}")
+
+    # Compare files
+    if args["lines"]:
+        matches = lines(file1, file2)
+    elif args["sentences"]:
+        matches = sentences(file1, file2)
+    elif args["substrings"]:
+        matches = substrings(file1, file2, args["substrings"])
+
+    # Output matches, sorted from longest to shortest, with line endings escaped
+    for match in sorted(matches, key=len, reverse=True):
+        print(match.replace("\n", "\\n").replace("\r", "\\r"))
+
+
+def positive(string):
+    """Convert string to a positive integer."""
+    value = int(string)
+    if value <= 0:
+        raise argparse.ArgumentTypeError("invalid length")
+    return value
+
+
+if __name__ == "__main__":
+    main()

pSet7/similarities/helpers.py

@@ -0,0 +1,62 @@
+from nltk.tokenize import sent_tokenize
+
+
+def lines(a, b):
+    """Return lines in both a and b"""
+    lines = []
+    # Split string a into lines: \n
+    # For each lines:
+    for line in a.split("\n"):
+        # Split string b into lines: \n
+        # Check if line from a appears in b
+        if line in b.split("\n"):
+            # Check if the line is empty
+            if line != "":
+                # If not empty, append to list
+                lines.append(line)
+    return lines
+
+
+def sentences(a, b):
+    """Return sentences in both a and b"""
+    sentences = []
+    # Using sent_tokenize(text, language)
+    # To divide string into sentences, EN language
+    a = sent_tokenize(a, language='english')
+    b = sent_tokenize(b, language='english')
+    # For each sentence in a:
+    for sentence in a:
+        # Check if sentence from is also in b
+        if sentence in b:
+            # Check if sentence is empty
+            # Check if not already in the list
+            if sentence != "" and sentence not in sentences:
+                # If not, append to list
+                sentences.append(sentence)
+    return sentences
+
+
+def substrings(a, b, n):
+    """Return substrings of length n in both a and b"""
+    substrings = []
+    a_substrings = get_substrings(a, n)
+    b_substrings = get_substrings(b, n)
+    # For every substring in list of substrings a:
+    for a_substring in a_substrings:
+        # For every substring in list of substrings b:
+        for b_substring in b_substrings:
+            # Check if substring from a is equivalent to substring from b
+            # Check if substring from a is not already in substrings' list
+            if a_substring == b_substring and a_substring not in substrings:
+                # If not, append to substrings
+                substrings.append(a_substring)
+    return substrings
+
+
+# Get substrings of length n of string s
+def get_substrings(s, n):
+    substrings = []
+    for i in range(len(s) - n + 1):
+        # string[start: end: step]
+        substrings.append(s[i:i + n])
+    return substrings

pSet7/similarities/inputs/Genesis-ASV.txt

@@ -0,0 +1 @@
+In the beginning God created the heavens and the earth. And the earth was waste and void; and darkness was upon the face of the deep: and the Spirit of God moved upon the face of the waters. And God said, Let there be light: and there was light.

pSet7/similarities/inputs/Genesis-ESV.txt

@@ -0,0 +1 @@
+In the beginning, God created the heavens and the earth. The earth was without form and void, and darkness was over the face of the deep. And the Spirit of God was hovering over the face of the waters. And God said, "Let there be light," and there was light.

pSet7/similarities/inputs/Genesis-KJV.txt

@@ -0,0 +1 @@
+In the beginning God created the heaven and the earth. And the earth was without form, and void; and darkness was upon the face of the deep. And the Spirit of God moved upon the face of the waters. And God said, Let there be light: and there was light.

pSet7/similarities/inputs/LesMis1.txt

@@ -0,0 +1 @@
+To love, or to have loved,this suffices. Demand nothing more. There is no other pearl to be found in the shadowy folds of life.

pSet7/similarities/inputs/LesMis2.txt

@@ -0,0 +1 @@
+To love or have loved, that is enough. Ask nothing further. There is no other pearl to be found in the dark folds of life.

pSet7/similarities/inputs/LittlePrince_HowardTranslation.txt

@@ -0,0 +1,6 @@
+"Goodbye," said the fox. "Here is my secret. It's quite simple: One sees clearly only with the heart. Anything essential is invisible to the eyes."
+"Anything essential is invisible to the eyes," the little prince repeated, in order to remember.
+"It's the time you spend on your rose that makes your rose so important."
+"It's the time I spent on my rose...," the little prince repeated, in order to remember.
+"People have forgotten this truth," the fox said. "But you mustn't forget it. You become responsible forever for what you've tamed. You're responsible for your rose..."
+"I'm responsible for my rose...," the little prince repeated, in order to remember.

pSet7/similarities/inputs/LittlePrince_WoodsTranslation.txt

@@ -0,0 +1,6 @@
+"Goodbye," said the fox. "And now here is my secret, a very simple secret: It is only with the heart that one can see rightly; what is essential is invisible to the eye."
+"What is essential is invisible to the eye," the little prince repeated, so that he would be sure to remember.
+"It is the time you have wasted for your rose that makes your rose so important."
+"It is the time I have wasted for my rose--" said the little prince, so that he would be sure to remember.
+"Men have forgotten this truth," said the fox." But you must not forget it. You become responsible, forever, for what you have tamed. You are responsible for your rose . . ."
+"I am responsible for my rose," the little prince repeated, so that he would be sure to remember.

pSet7/similarities/inputs/TheStrangerCamus_GilbertTranslation.txt

@@ -0,0 +1 @@
+Raymond rang me up at the office. He said that a friend of histo whom he'd spoken about meinvited me to spend next Sunday at his little seaside bungalow just outside Algiers. I told him I'd have been delighted; only I had promised to spend Sunday with a girl. Raymond promptly replied that she could come, too. In fact, his friend's wife would be very pleased not to be the only woman in a party of men. 

pSet7/similarities/inputs/TheStrangerCamus_WardTranslation.txt

@@ -0,0 +1 @@
+Raymond called me at the office. He told me that a friend of his (he'd spoken to him about me) had invited me to spend the day Sunday at his little beach house, near Algiers. I said I'd really like to, but I'd promised to spend the day with a girlfriend. Raymond immediately told me she was invited too. His friend's wife would be very glad not to be alone with a bunch of men.

pSet7/similarities/inputs/compare-1.c

@@ -0,0 +1,19 @@
+#include <cs50.h>
+#include <stdio.h>
+
+int main(void)
+{
+    // get two strings
+    string s = get_string("s: ");
+    string t = get_string("t: ");
+
+    // compare strings' addresses
+    if (s == t)
+    {
+        printf("same\n");
+    }
+    else
+    {
+        printf("different\n");
+    }
+}

pSet7/similarities/inputs/compare-2.c

@@ -0,0 +1,20 @@
+#include <cs50.h>
+#include <stdio.h>
+
+int main(void)
+{
+    // get two strings
+    char *s = get_string("s: ");
+    char *t = get_string("t: ");
+
+    // compare strings' addresses
+    if (s == t)
+    {
+        printf("same\n");
+    }
+    else
+    {
+        printf("not same\n");
+    }
+}
+

pSet7/similarities/inputs/hello.c

@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+    printf("hello, world\n");
+}

pSet7/similarities/inputs/hey.c

@@ -0,0 +1,6 @@
+#include <stdio.h>
+
+int main(void)
+{
+    printf("hey, world\n");
+}

pSet7/similarities/inputs/swap-1.c

@@ -0,0 +1,20 @@
+#include <stdio.h>
+
+void swap(int *a, int *b);
+
+int main(void)
+{
+    int x = 1;
+    int y = 2;
+
+    printf("x is %i, y is %i\n", x, y);
+    swap(&x, &y);
+    printf("x is %i, y is %i\n", x, y);
+}
+
+void swap(int *a, int *b)
+{
+    int tmp = *a;
+    *a = *b;
+    *b = tmp;
+}