interp: Implement "matches"

interp/match.go

@@ -1,156 +1,11 @@
 package interp
 
-import (
-	"errors"
-	"fmt"
-	"net/mail"
-	"strconv"
-	"strings"
-	"unicode"
-)
+import "github.com/foxcpp/go-sieve/interp/match"
 
-type Match string
-
-const (
-	MatchContains Match = "contains"
-	MatchIs       Match = "is"
-	MatchMatches  Match = "matches"
-)
-
-type Comparator string
-
-const (
-	ComparatorOctet          Comparator = "i;octet"
-	ComparatorASCIICaseMap   Comparator = "i;ascii-casemap"
-	ComparatorASCIINumeric   Comparator = "i;ascii-numeric"
-	ComparatorUnicodeCaseMap Comparator = "i;unicode-casemap"
-)
-
-type AddressPart string
-
-const (
-	LocalPart AddressPart = "localpart"
-	Domain    AddressPart = "domain"
-	All       AddressPart = "all"
-)
-
-func split(addr string) (mailbox, domain string, err error) {
-	if strings.EqualFold(addr, "postmaster") {
-		return addr, "", nil
-	}
-
-	indx := strings.LastIndexByte(addr, '@')
-	if indx == -1 {
-		return "", "", errors.New("address: missing at-sign")
-	}
-	mailbox = addr[:indx]
-	domain = addr[indx+1:]
-	if mailbox == "" {
-		return "", "", errors.New("address: empty local-part")
-	}
-	if domain == "" {
-		return "", "", errors.New("address: empty domain")
-	}
-	return
+func matchOctet(pattern, value string) (bool, error) {
+	return match.Match([]byte(pattern), []byte(value))
 }
 
-var ErrComparatorMatchUnsupported = fmt.Errorf("match-comparator combination not supported")
-
-func matchString(pattern, key string) (bool, error) {
-	// FIXME: This does not account for comparator differences.
-	panic("match is not implemented")
-}
-
-func numericValue(s string) *uint64 {
-	if len(s) == 0 {
-		return nil
-	}
-	runes := []rune(s)
-	if !unicode.IsDigit(runes[0]) {
-		return nil
-	}
-	var sl string
-	for i, r := range runes {
-		if !unicode.IsDigit(r) {
-			sl = string(runes[:i])
-		}
-	}
-	digit, _ := strconv.ParseUint(sl, 10, 64)
-	return &digit
-}
-
-func testString(comparator Comparator, match Match, value, key string) (bool, error) {
-	switch comparator {
-	case ComparatorOctet:
-		switch match {
-		case MatchContains:
-			return strings.Contains(value, key), nil
-		case MatchIs:
-			return value == key, nil
-		case MatchMatches:
-			return matchString(key, value)
-		}
-	case ComparatorASCIINumeric:
-		switch match {
-		case MatchContains:
-			return false, ErrComparatorMatchUnsupported
-		case MatchIs:
-			lhsNum := numericValue(value)
-			rhsNum := numericValue(key)
-			if lhsNum == nil || rhsNum == nil {
-				return false, nil
-			}
-			return *lhsNum == *rhsNum, nil
-		case MatchMatches:
-			return false, ErrComparatorMatchUnsupported
-		}
-	case ComparatorASCIICaseMap:
-		// FIXME: Case-fold ASCII only.
-		fallthrough
-	case ComparatorUnicodeCaseMap:
-		value = strings.ToLower(value)
-		key = strings.ToLower(key)
-		switch match {
-		case MatchContains:
-			return strings.Contains(value, key), nil
-		case MatchIs:
-			return value == key, nil
-		case MatchMatches:
-			return matchString(value, key)
-		}
-	}
-	return false, nil
-}
-
-func testAddress(part AddressPart, comparator Comparator, match Match, headerVal []*mail.Address, addrValue string) (bool, error) {
-	for _, addr := range headerVal {
-		var valueToCompare string
-		if addr.Address != "" {
-			switch part {
-			case LocalPart:
-				localPart, _, err := split(addr.Address)
-				if err != nil {
-					continue
-				}
-				valueToCompare = localPart
-			case Domain:
-				_, domain, err := split(addr.Address)
-				if err != nil {
-					continue
-				}
-				valueToCompare = domain
-			case All:
-				valueToCompare = addr.Address
-			}
-		}
-
-		ok, err := testString(comparator, match, valueToCompare, addrValue)
-		if err != nil {
-			return false, err
-		}
-		if ok {
-			return true, nil
-		}
-	}
-	return false, nil
+func matchUnicode(pattern, value string) (bool, error) {
+	return match.Match([]rune(pattern), []rune(value))
 }

interp/match/match.go

@@ -0,0 +1,140 @@
+// Copyright 2010 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package match
+
+import (
+	"errors"
+)
+
+// ErrBadPattern indicates a pattern was malformed.
+var ErrBadPattern = errors.New("syntax error in pattern")
+
+// Match is a simplified version of path.Match that removes support
+// for character classes and operates on already decoded input ([]byte or []rune).
+func Match[T rune | byte](pattern, name []T) (matched bool, err error) {
+Pattern:
+	for len(pattern) > 0 {
+		var star bool
+		var chunk []T
+		star, chunk, pattern = scanChunk(pattern)
+		if star && len(chunk) == 0 {
+			return true, nil
+		}
+		// Look for match at current position.
+		t, ok, err := matchChunk(chunk, name)
+		// if we're the last chunk, make sure we've exhausted the name
+		// otherwise we'll give a false result even if we could still match
+		// using the star
+		if ok && (len(t) == 0 || len(pattern) > 0) {
+			name = t
+			continue
+		}
+		if err != nil {
+			return false, err
+		}
+		if star {
+			// Look for match skipping i+1 bytes.
+			for i := 0; i < len(name); i++ {
+				t, ok, err := matchChunk(chunk, name[i+1:])
+				if ok {
+					// if we're the last chunk, make sure we exhausted the name
+					if len(pattern) == 0 && len(t) > 0 {
+						continue
+					}
+					name = t
+					continue Pattern
+				}
+				if err != nil {
+					return false, err
+				}
+			}
+		}
+		// Before returning false with no error,
+		// check that the remainder of the pattern is syntactically valid.
+		for len(pattern) > 0 {
+			_, chunk, pattern = scanChunk(pattern)
+			if _, _, err := matchChunk(chunk, []T{}); err != nil {
+				return false, err
+			}
+		}
+		return false, nil
+	}
+	return len(name) == 0, nil
+}
+
+// scanChunk gets the next segment of pattern, which is a non-star string
+// possibly preceded by a star.
+func scanChunk[T rune | byte](pattern []T) (star bool, chunk, rest []T) {
+	for len(pattern) > 0 && pattern[0] == '*' {
+		pattern = pattern[1:]
+		star = true
+	}
+	inrange := false
+	var i int
+Scan:
+	for i = 0; i < len(pattern); i++ {
+		switch pattern[i] {
+		case '\\':
+			// error check handled in matchChunk: bad pattern.
+			if i+1 < len(pattern) {
+				i++
+			}
+		case '[':
+			inrange = true
+		case ']':
+			inrange = false
+		case '*':
+			if !inrange {
+				break Scan
+			}
+		}
+	}
+	return star, pattern[0:i], pattern[i:]
+}
+
+// matchChunk checks whether chunk matches the beginning of s.
+// If so, it returns the remainder of s (after the match).
+// Chunk is all single-character operators: literals, char classes, and ?.
+func matchChunk[T rune | byte](chunk, s []T) (rest []T, ok bool, err error) {
+	// failed records whether the match has failed.
+	// After the match fails, the loop continues on processing chunk,
+	// checking that the pattern is well-formed but no longer reading s.
+	failed := false
+	for len(chunk) > 0 {
+		if !failed && len(s) == 0 {
+			failed = true
+		}
+		switch chunk[0] {
+		case '?':
+			if !failed {
+				if s[0] == '/' {
+					failed = true
+				}
+				s = s[1:]
+			}
+			chunk = chunk[1:]
+
+		case '\\':
+			chunk = chunk[1:]
+			if len(chunk) == 0 {
+				return []T{}, false, ErrBadPattern
+			}
+			fallthrough
+
+		default:
+			if !failed {
+				if chunk[0] != s[0] {
+					failed = true
+				}
+				s = s[1:]
+			}
+			chunk = chunk[1:]
+		}
+	}
+	if failed {
+		return []T{}, false, nil
+	}
+	return s, true, nil
+}