request line and http headers parsing completed

Author: arkahood

Makefile

@@ -1,2 +1,2 @@
 run:
-	go run ./cmd/tcplistener/
+	go run ./cmd/tcplistener/ | tee tcplistener.log

README.md

@@ -1,2 +1,21 @@
 # RawHTTP
 HTTP 1.1 server from scratch
+
+## HTTP Message Structure
+
+According to RFC 7230, HTTP messages follow this structure:
+
+```
+start-line CRLF
+*( field-line CRLF )
+*( field-line CRLF )
+...
+CRLF
+[ message-body ]
+```
+
+Where:
+- **start-line**: Request line (method, URI, version) or status line
+- **field-line**: HTTP headers (key-value pairs) (The RFC uses the term)
+- **CRLF**: Carriage return + line feed (`\r\n`)
+- **message-body**: Optional request/response body

cmd/tcplistener/main.go

@@ -1,55 +1,11 @@
 package main
 
 import (
+	"RAWHTTP/internal/request"
 	"fmt"
-	"io"
 	"net"
-	"strings"
 )
 
-func getLinesChannel(f io.ReadCloser) <-chan string {
-	lines := make(chan string)
-
-	go func() {
-		defer f.Close()
-		defer close(lines)
-
-		currentLine := ""
-
-		for {
-			read := make([]byte, 8)
-			_, err := f.Read(read)
-
-			if err == io.EOF {
-				// Send the last line if it has content
-				if currentLine != "" {
-					lines <- currentLine
-				}
-				return
-			}
-
-			if err != nil {
-				fmt.Println("Some Error Happened While Putting in Slice")
-				return
-			}
-
-			parts := strings.Split(string(read), "\n")
-
-			// Process all parts except the last one, which may be incomplete
-			if len(parts)-1 > 0 {
-				currentLine += parts[0]
-				lines <- currentLine
-				currentLine = "" // Reset for next line
-			}
-
-			// The last part, which may be incomplete gets added to currentLine
-			currentLine += parts[len(parts)-1]
-		}
-	}()
-
-	return lines
-}
-
 func main() {
 	listener, err := net.Listen("tcp", ":42069")
 
@@ -66,10 +22,19 @@ func main() {
 		}
 
 		go func(c net.Conn) {
-			lines := getLinesChannel(conn)
+			req, err := request.RequestFromReader(conn)
+
+			if err != nil {
+				fmt.Println("error happened", err.Error())
+			}
 
-			for line := range lines {
-				fmt.Println(line)
+			fmt.Println("Request line:")
+			fmt.Println("Method: ", req.RequestLine.Method)
+			fmt.Println("Http Version: ", req.RequestLine.HttpVersion)
+			fmt.Println("Target: ", req.RequestLine.RequestTarget)
+			fmt.Println("Headers")
+			for key, val := range req.Headers {
+				fmt.Println(key, ": ", val)
 			}
 		}(conn)
 	}

go.mod

@@ -1,3 +1,10 @@
 module RAWHTTP
 
 go 1.25.3
+
+require (
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/stretchr/testify v1.11.1 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)

go.sum

@@ -0,0 +1,9 @@
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

internal/headers/headers.go

@@ -0,0 +1,88 @@
+package headers
+
+import (
+	"errors"
+	"strings"
+	"unicode"
+)
+
+const FieldLineSeperator = ":"
+const crlf = "\r\n"
+
+type Headers map[string]string
+
+// there can be an unlimited amount of whitespace
+// before and after the field-value (Header value). However, when parsing a field-name,
+// there must be no spaces betwixt the colon and the field-name. In other words,
+// these are valid:
+
+// 'Host: localhost:42069'
+// '          Host: localhost:42069    '
+
+// But this is not:
+
+// Host : localhost:42069
+
+func (h Headers) Parse(data []byte) (n int, done bool, err error) {
+	endIdx := strings.Index(string(data), crlf)
+	if endIdx == -1 {
+		return 0, false, nil
+	}
+	// if encounter \r\n in front of line that means we consumed all the headers/fieldLines
+	if endIdx == 0 {
+		return endIdx + 2, true, nil
+	}
+
+	currentLine := string(data[:endIdx])
+	fieldParts := strings.SplitN(currentLine, FieldLineSeperator, 2)
+
+	if len(fieldParts) != 2 {
+		return 0, false, errors.New("field-line have wrong number of parts")
+	}
+
+	fieldName := strings.TrimLeft(fieldParts[0], " ")
+	if len(fieldName) != len(strings.TrimSpace(fieldName)) {
+		return 0, false, errors.New("error in field-name syntax, whitespace unexpected")
+	}
+	if !isValidFieldName(fieldName) {
+		return 0, false, errors.New("invalid characters in field-name")
+	}
+
+	fieldValue := strings.TrimSpace(strings.Trim(fieldParts[1], crlf))
+	// lowercase the fieldname while adding to the map
+	val, exists := h[strings.ToLower(fieldName)]
+	if exists {
+		h[strings.ToLower(fieldName)] = val + "," + fieldValue
+	} else {
+		h[strings.ToLower(fieldName)] = fieldValue
+	}
+
+	return endIdx + 2, false, nil
+}
+
+func isValidFieldName(fieldName string) bool {
+	allowedSpecials := map[rune]bool{
+		'!': true, '#': true, '$': true, '%': true, '&': true, '\'': true,
+		'*': true, '+': true, '-': true, '.': true, '^': true, '_': true,
+		'`': true, '|': true, '~': true,
+	}
+
+	if len(fieldName) == 0 {
+		return false
+	}
+
+	for _, ch := range fieldName {
+		switch {
+		case unicode.IsLetter(ch):
+			continue
+		case unicode.IsDigit(ch):
+			continue
+		case allowedSpecials[ch]:
+			continue
+		default:
+			return false
+		}
+	}
+
+	return true
+}

internal/headers/headers_test.go

@@ -0,0 +1,57 @@
+package headers
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestHeadersParser(t *testing.T) {
+	// Test: Valid single header
+	headers := make(Headers)
+	data := []byte("host: localhost:42069\r\n\r\n")
+	n, done, err := headers.Parse(data)
+	require.NoError(t, err)
+	require.NotNil(t, headers)
+	assert.Equal(t, "localhost:42069", headers["host"])
+	assert.Equal(t, 23, n)
+	assert.False(t, done)
+
+	// Test: Invalid spacing header
+	headers = make(Headers)
+	data = []byte("       Host : localhost:42069       \r\n\r\n")
+	n, done, err = headers.Parse(data)
+	require.Error(t, err)
+	assert.Equal(t, 0, n)
+	assert.False(t, done)
+
+	// Test: Invalid character in header
+	headers = make(Headers)
+	data = []byte("       H(st : localhost:42069       \r\n\r\n")
+	n, done, err = headers.Parse(data)
+	require.Error(t, err)
+	assert.Equal(t, 0, n)
+	assert.False(t, done)
+
+	// Test: Uppercase FieldName should add as a lowercase key
+	headers = make(Headers)
+	data = []byte("Host: localhost:42069\r\n\r\n")
+	n, done, err = headers.Parse(data)
+	require.NoError(t, err)
+	require.NotNil(t, headers)
+	assert.Equal(t, "localhost:42069", headers["host"])
+	assert.Equal(t, 23, n)
+	assert.False(t, done)
+
+	// Test: multipe same fieldname should have values comma separated
+	headers = make(Headers)
+	data = []byte("Host: localhost:42069\r\nHost: localhost:42070\r\n\r\n")
+	bytesConsumed0, _, _ := headers.Parse(data)
+	bytesConsumed1, done, err := headers.Parse(data[bytesConsumed0:])
+	require.NoError(t, err)
+	require.NotNil(t, headers)
+	assert.Equal(t, "localhost:42069,localhost:42070", headers["host"])
+	assert.Equal(t, bytesConsumed0+bytesConsumed1, len(data)-2)
+	assert.False(t, done)
+}