From 434965ca6701aa9939a56b1ba8563a786461d6db Mon Sep 17 00:00:00 2001
From: David Dworken <david@daviddworken.com>
Date: Mon, 11 Dec 2023 21:07:09 -0800
Subject: [PATCH] Add support for quoted searchs for exact matches, for #135

---
 README.md              |  3 +--
 client/lib/lib.go      |  8 ++++++--
 client/lib/lib_test.go | 22 +++++++++++++++-------
 3 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index 4afcba3d..d7e827a0 100644
--- a/README.md
+++ b/README.md
@@ -38,7 +38,7 @@ Both support the same query format, see the below annotated queries:
 |---|---|
 | `psql` | Find all commands containing `psql` |
 | `psql db.example.com` | Find all commands containing `psql` and `db.example.com` |
-| `docker hostname:my-server` | Find all commands containing `docker` that were run on the computer with hostname `my-server` |
+| `"docker run" hostname:my-server` | Find all commands containing `docker run` that were run on the computer with hostname `my-server` |
 | `nano user:root` | Find all commands containing `nano` that were run as `root` |
 | `exit_code:127` | Find all commands that exited with code `127` |
 | `service before:2022-02-01` | Find all commands containing `service` run before February 1st 2022 |
@@ -74,7 +74,6 @@ If you would like to:
 
 </details>
 
-
 <details>
 <summary>TUI key bindings</summary>
 The TUI (opened via `Control+R`) supports a number of key bindings:
diff --git a/client/lib/lib.go b/client/lib/lib.go
index ebbb0773..8a680f17 100644
--- a/client/lib/lib.go
+++ b/client/lib/lib.go
@@ -978,19 +978,23 @@ func tokenize(query string) []string {
 	return splitEscaped(query, ' ', -1)
 }
 
+// TODO: Maybe add support for searching for the backslash character itself?
 func splitEscaped(query string, separator rune, maxSplit int) []string {
 	var token []rune
 	var tokens []string
 	splits := 1
 	runeQuery := []rune(query)
+	isInQuotedString := false
 	for i := 0; i < len(runeQuery); i++ {
-		if (maxSplit < 0 || splits < maxSplit) && runeQuery[i] == separator {
+		if (maxSplit < 0 || splits < maxSplit) && runeQuery[i] == separator && !isInQuotedString {
 			tokens = append(tokens, string(token))
 			token = token[:0]
 			splits++
 		} else if runeQuery[i] == '\\' && i+1 < len(runeQuery) {
-			token = append(token, runeQuery[i], runeQuery[i+1])
 			i++
+			token = append(token, runeQuery[i])
+		} else if runeQuery[i] == '"' {
+			isInQuotedString = !isInQuotedString
 		} else {
 			token = append(token, runeQuery[i])
 		}
diff --git a/client/lib/lib_test.go b/client/lib/lib_test.go
index 61a60d26..60639d03 100644
--- a/client/lib/lib_test.go
+++ b/client/lib/lib_test.go
@@ -257,7 +257,7 @@ func TestContainsUnescaped(t *testing.T) {
 	for _, tc := range testcases {
 		actual := containsUnescaped(tc.input, tc.token)
 		if !reflect.DeepEqual(actual, tc.expected) {
-			t.Fatalf("containsUnescaped failure for containsUnescaped(%#v, %#v), actual=%#v", tc.input, tc.token, actual)
+			t.Fatalf("failure for containsUnescaped(%#v, %#v), actual=%#v", tc.input, tc.token, actual)
 		}
 	}
 }
@@ -274,16 +274,24 @@ func TestSplitEscaped(t *testing.T) {
 		{"foo bar baz", ' ', 3, []string{"foo", "bar", "baz"}},
 		{"foo bar baz", ' ', 1, []string{"foo bar baz"}},
 		{"foo bar baz", ' ', -1, []string{"foo", "bar", "baz"}},
-		{"foo\\ bar baz", ' ', -1, []string{"foo\\ bar", "baz"}},
-		{"foo\\bar baz", ' ', -1, []string{"foo\\bar", "baz"}},
-		{"foo\\bar baz foob", ' ', 2, []string{"foo\\bar", "baz foob"}},
-		{"foo\\ bar\\ baz", ' ', -1, []string{"foo\\ bar\\ baz"}},
-		{"foo\\ bar\\  baz", ' ', -1, []string{"foo\\ bar\\ ", "baz"}},
+		{"foo\\ bar baz", ' ', -1, []string{"foo bar", "baz"}},
+		{"foo\\bar baz", ' ', -1, []string{"foobar", "baz"}},
+		{"foo\\bar baz foob", ' ', 2, []string{"foobar", "baz foob"}},
+		{"foo\\ bar\\ baz", ' ', -1, []string{"foo bar baz"}},
+		{"foo\\ bar\\  baz", ' ', -1, []string{"foo bar ", "baz"}},
+		{"\"foo bar\"", ' ', -1, []string{"foo bar"}},
+		{"\"foo bar\" \"   \"", ' ', -1, []string{"foo bar", "   "}},
+		{"\"foo bar baz\" and", ' ', -1, []string{"foo bar baz", "and"}},
+		{"\"foo bar baz\" and", ' ', -1, []string{"foo bar baz", "and"}},
+		{"\"foo bar baz", ' ', -1, []string{"foo bar baz"}},
+		{"\"foo bar baz\\\"\"", ' ', -1, []string{"foo bar baz\""}},
+		{"cwd:\"foo bar :baz\\\"\"", ':', -1, []string{"cwd", "foo bar :baz\""}},
+		{"cwd:\"foo bar :baz\\\"\"", ' ', -1, []string{"cwd:foo bar :baz\""}},
 	}
 	for _, tc := range testcases {
 		actual := splitEscaped(tc.input, tc.char, tc.limit)
 		if !reflect.DeepEqual(actual, tc.expected) {
-			t.Fatalf("containsUnescaped failure for splitEscaped(%#v, %#v, %#v), actual=%#v", tc.input, string(tc.char), tc.limit, actual)
+			t.Fatalf("failure for splitEscaped(%#v, %#v, %#v), actual=%#v", tc.input, string(tc.char), tc.limit, actual)
 		}
 	}
 }