From 39e410aa46c73a51707b4c8cdd8b5bb702665d6d Mon Sep 17 00:00:00 2001
From: Dmytro Maluka <dmitrymaluka@gmail.com>
Date: Sat, 23 Mar 2024 21:24:44 +0100
Subject: [PATCH] UpdateRules: reintroduce using header regex for filetype
 detection

Replacing header patterns with signature patterns was a mistake, since
both are quite different from each other, and both have their uses. In
fact, this caused a serious regression: for such files as shell scripts
without *.sh extension but with #!/bin/sh inside, filetype detection
does not work at all anymore.

Since both header and signature patterns are useful, reintroduce support
for header patterns while keeping support for signature patterns as well
and make both work nicely together.

Also, unlike in the old implementation (before signatures were
introduced), ensure that filename matches take precedence over header
matches, i.e. if there is at least one filename match found, all header
matches are ignored. This makes the behavior more deterministic and
prevents previously observed issues like #2894 and #3054: wrongly
detected filetypes caused by some overly general header patterns.

Precisely, the new behavior is:

1. if there is at least one filename match, use filename matches only
2. if there are no filename matches, use header matches
3. in both cases, try to use signatures to find the best match among
multiple filename or header matches
---
 internal/buffer/buffer.go | 51 +++++++++++++++++++++++++++++----------
 1 file changed, 38 insertions(+), 13 deletions(-)

diff --git a/internal/buffer/buffer.go b/internal/buffer/buffer.go
index 228af183..0f21f188 100644
--- a/internal/buffer/buffer.go
+++ b/internal/buffer/buffer.go
@@ -702,6 +702,7 @@ func (b *Buffer) UpdateRules() {
 	}
 
 	fnameMatches := []syntaxFileBuffer{}
+	headerMatches := []syntaxFileBuffer{}
 	syntaxFile := ""
 	foundDef := false
 	var header *highlight.Header
@@ -719,7 +720,19 @@ func (b *Buffer) UpdateRules() {
 			continue
 		}
 
-		if ((ft == "unknown" || ft == "") && header.MatchFileName(b.Path)) || header.FileType == ft {
+		matchedFileName := false
+		matchedFileHeader := false
+
+		if ft == "unknown" || ft == "" {
+			if header.MatchFileName(b.Path) {
+				matchedFileName = true
+			}
+			if len(fnameMatches) == 0 && header.MatchFileHeader(b.lines[0].data) {
+				matchedFileHeader = true
+			}
+		}
+
+		if matchedFileName || matchedFileHeader || header.FileType == ft {
 			file, err := highlight.ParseFile(data)
 			if err != nil {
 				screen.TermMessage("Error parsing syntax file " + f.Name() + ": " + err.Error())
@@ -737,8 +750,12 @@ func (b *Buffer) UpdateRules() {
 				syntaxFile = f.Name()
 				foundDef = true
 				break
-			} else {
+			}
+
+			if matchedFileName {
 				fnameMatches = append(fnameMatches, syntaxFileBuffer{header, f.Name(), syndef})
+			} else if matchedFileHeader {
+				headerMatches = append(headerMatches, syntaxFileBuffer{header, f.Name(), syndef})
 			}
 		}
 	}
@@ -762,6 +779,9 @@ func (b *Buffer) UpdateRules() {
 				if header.MatchFileName(b.Path) {
 					fnameMatches = append(fnameMatches, syntaxFileBuffer{header, f.Name(), nil})
 				}
+				if len(fnameMatches) == 0 && header.MatchFileHeader(b.lines[0].data) {
+					headerMatches = append(headerMatches, syntaxFileBuffer{header, f.Name(), nil})
+				}
 			} else if header.FileType == ft {
 				syntaxFile = f.Name()
 				break
@@ -770,7 +790,12 @@ func (b *Buffer) UpdateRules() {
 	}
 
 	if syntaxFile == "" {
-		length := len(fnameMatches)
+		matches := fnameMatches
+		if len(matches) == 0 {
+			matches = headerMatches
+		}
+
+		length := len(matches)
 		if length > 0 {
 			signatureMatch := false
 			if length > 1 {
@@ -781,15 +806,15 @@ func (b *Buffer) UpdateRules() {
 					limit = detectlimit
 				}
 				for i := 0; i < length && !signatureMatch; i++ {
-					if fnameMatches[i].header.HasFileSignature() {
+					if matches[i].header.HasFileSignature() {
 						for j := 0; j < limit && !signatureMatch; j++ {
-							if fnameMatches[i].header.MatchFileSignature(b.lines[j].data) {
-								syntaxFile = fnameMatches[i].fileName
-								if fnameMatches[i].syntaxDef != nil {
-									b.SyntaxDef = fnameMatches[i].syntaxDef
+							if matches[i].header.MatchFileSignature(b.lines[j].data) {
+								syntaxFile = matches[i].fileName
+								if matches[i].syntaxDef != nil {
+									b.SyntaxDef = matches[i].syntaxDef
 									foundDef = true
 								}
-								header = fnameMatches[i].header
+								header = matches[i].header
 								signatureMatch = true
 							}
 						}
@@ -797,12 +822,12 @@ func (b *Buffer) UpdateRules() {
 				}
 			}
 			if length == 1 || !signatureMatch {
-				syntaxFile = fnameMatches[0].fileName
-				if fnameMatches[0].syntaxDef != nil {
-					b.SyntaxDef = fnameMatches[0].syntaxDef
+				syntaxFile = matches[0].fileName
+				if matches[0].syntaxDef != nil {
+					b.SyntaxDef = matches[0].syntaxDef
 					foundDef = true
 				}
-				header = fnameMatches[0].header
+				header = matches[0].header
 			}
 		}
 	}