From a5b11540f47d605189a06ac15b56117193b4758f Mon Sep 17 00:00:00 2001
From: Sean Luo <sluo2@clm-c02n111cfd59.enova.com>
Date: Mon, 17 Jun 2019 14:45:21 -0500
Subject: [PATCH] new branch

---
 exercise-001-corpus/word_count/main.go      | 96 +++++++++++++++++++++
 exercise-001-corpus/word_count/main_test.go | 30 +++++++
 2 files changed, 126 insertions(+)
 create mode 100644 exercise-001-corpus/word_count/main.go
 create mode 100644 exercise-001-corpus/word_count/main_test.go

diff --git a/exercise-001-corpus/word_count/main.go b/exercise-001-corpus/word_count/main.go
new file mode 100644
index 0000000..96889f0
--- /dev/null
+++ b/exercise-001-corpus/word_count/main.go
@@ -0,0 +1,96 @@
+package main
+
+import (
+	"bufio"
+	"fmt"
+	"os"
+	"sort"
+	"strings"
+)
+
+/*
+*  This program counts the words in a text file and outputs the counts in decreasing order.
+*  Command line: word_count <fileName.txt>
+ */
+func main() {
+	fileName := os.Args[1] // extract file name of text
+
+	// get dictionary
+	rawWordCount, err := ScanWords(fileName)
+	if err != nil {
+		panic(err)
+	}
+
+	// sort dictionary
+	orderedDict := rankByWordCount(rawWordCount)
+	for _, pair := range orderedDict {
+		fmt.Println(pair.Value, pair.Key)
+	}
+}
+
+/*
+*  ScanWords -- This function takes in a file name and returns a dictionary of word-count pairs
+ */
+func ScanWords(path string) (map[string]int, error) {
+	// open file
+	file, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	scanner.Split(bufio.ScanWords)
+
+	dict := make(map[string]int)
+	// go through all words, forcing lowercase & removing punctuations
+	for scanner.Scan() {
+		curWord := strings.ToLower(scanner.Text())      // force lowercase
+		curWord = strings.Replace(curWord, ".", "", -1) // remove special characters
+		curWord = strings.Replace(curWord, ",", "", -1)
+		curWord = strings.Replace(curWord, "?", "", -1)
+		curWord = strings.Replace(curWord, ":", "", -1)
+		if curWord[0] == '"' {
+			curWord = curWord[1:]
+		}
+		if curWord[len(curWord)-1] == '"' {
+			curWord = curWord[:len(curWord)-1]
+		}
+
+		if count, isIn := dict[curWord]; isIn {
+			dict[curWord] = count + 1 // word has been seen before, increment count
+		} else {
+			dict[curWord] = 1 // new word, add to dict
+		}
+	}
+
+	return dict, nil
+}
+
+/*
+*  Below is an implementation for sorting a map by value
+ */
+func rankByWordCount(wordFrequencies map[string]int) PairList {
+	pl := make(PairList, len(wordFrequencies))
+	i := 0
+	for k, v := range wordFrequencies {
+		pl[i] = Pair{k, v}
+		i++
+	}
+	sort.Sort(sort.Reverse(pl))
+	return pl
+}
+
+// Pair struct used for sorting map by value
+type Pair struct {
+	Key   string
+	Value int
+}
+
+// PairList struct used to contain Pair types
+type PairList []Pair
+
+func (p PairList) Len() int           { return len(p) }
+func (p PairList) Less(i, j int) bool { return p[i].Value < p[j].Value }
+func (p PairList) Swap(i, j int)      { p[i], p[j] = p[j], p[i] }
diff --git a/exercise-001-corpus/word_count/main_test.go b/exercise-001-corpus/word_count/main_test.go
new file mode 100644
index 0000000..1662f76
--- /dev/null
+++ b/exercise-001-corpus/word_count/main_test.go
@@ -0,0 +1,30 @@
+package main
+
+import (
+	"testing"
+)
+
+func TestWordCount(t *testing.T) {
+	dict, err := ScanWords("../7oldsamr.txt")
+	if err != nil {
+		panic(err)
+	}
+	v1 := dict["the"]
+	v2 := dict["and"]
+	v3 := dict["to"]
+	if v1 != 36 {
+		t.Error(
+			"For 'the' expected 36, got", v1,
+		)
+	}
+	if v2 != 18 {
+		t.Error(
+			"For 'and' expected 18, got", v2,
+		)
+	}
+	if v3 != 14 {
+		t.Error(
+			"For 'to' expected 14, got", v3,
+		)
+	}
+}