fix(config): remove trailing newlines in regexes (#373)v1.17.0-beta31.17.0-beta2

Closes #372

Fun YAML fact of the day:

What is the difference between how these two expressions are parsed?

```yaml
foo: >
  bar
```

```yaml
foo: >-
  bar
```

They are invisible in yaml, but when you evaluate them to JSON the
difference is obvious:

```json
{
  "foo": "bar\n"
}
```

```json
{
  "foo": "bar"
}
```

User-Agent strings, URL path values, and HTTP headers _do_ end in
newlines in HTTP/1.1 wire form, but that newline is usually stripped
before the server actually handles it. Also HTTP/2 is a thing and does
not terminate header values with newlines.

This change makes Anubis more aggressively detect mistaken uses of the
yaml `>` operator and nudges the user into using the yaml `>-` operator
which does not append the trailing newline.

I had honestly forgotten about this YAML behavior because it wasn't
relevant for so long. Oops! Glad I released a beta.

Whenever you get into this state, Anubis will throw a config parsing
error and then give you a message hinting at the folly of your ways.

```
config.Bot: regular expression ends with newline (try >- instead of > in yaml)
```

Big thanks to https://yaml-multiline.info, this helped me realize my
folly instantly.

@aiverson, this is official permission to say "told you so".

Signed-off-by: Xe Iaso <me@xeiaso.net>

1 files changed, 6 insertions, 6 deletions

diff --git a/lib/policy/checker.go b/lib/policy/checker.go
index ad98ced..51223cd 100644
--- a/lib/policy/checker.go
+++ b/lib/policy/checker.go
@@ -110,11 +110,11 @@ func NewUserAgentChecker(rexStr string) (Checker, error) {
 }
 
 func NewHeaderMatchesChecker(header, rexStr string) (Checker, error) {
-	rex, err := regexp.Compile(rexStr)
+	rex, err := regexp.Compile(strings.TrimSpace(rexStr))
 	if err != nil {
 		return nil, fmt.Errorf("%w: regex %s failed parse: %w", ErrMisconfiguration, rexStr, err)
 	}
-	return &HeaderMatchesChecker{header, rex, internal.SHA256sum(header + ": " + rexStr)}, nil
+	return &HeaderMatchesChecker{strings.TrimSpace(header), rex, internal.SHA256sum(header + ": " + rexStr)}, nil
 }
 
 func (hmc *HeaderMatchesChecker) Check(r *http.Request) (bool, error) {
@@ -135,7 +135,7 @@ type PathChecker struct {
 }
 
 func NewPathChecker(rexStr string) (Checker, error) {
-	rex, err := regexp.Compile(rexStr)
+	rex, err := regexp.Compile(strings.TrimSpace(rexStr))
 	if err != nil {
 		return nil, fmt.Errorf("%w: regex %s failed parse: %w", ErrMisconfiguration, rexStr, err)
 	}
@@ -155,7 +155,7 @@ func (pc *PathChecker) Hash() string {
 }
 
 func NewHeaderExistsChecker(key string) Checker {
-	return headerExistsChecker{key}
+	return headerExistsChecker{strings.TrimSpace(key)}
 }
 
 type headerExistsChecker struct {
@@ -180,11 +180,11 @@ func NewHeadersChecker(headermap map[string]string) (Checker, error) {
 
 	for key, rexStr := range headermap {
 		if rexStr == ".*" {
-			result = append(result, headerExistsChecker{key})
+			result = append(result, headerExistsChecker{strings.TrimSpace(key)})
 			continue
 		}
 
-		rex, err := regexp.Compile(rexStr)
+		rex, err := regexp.Compile(strings.TrimSpace(rexStr))
 		if err != nil {
 			errs = append(errs, fmt.Errorf("while compiling header %s regex %s: %w", key, rexStr, err))
 			continue