all: implement match-file-comment for seting comment based on file name

The first thing that the program do is to detect which comment string to
be used when inserting SPDX identifiers in the file.

For each pattern in the "match-file-comment" section, the program will
match it with file name to get the comment prefix and suffix to be used
later.

User can add their own "match-file-comment" section as they like or modify
the existing one.

The "match-file-comment" can have empty prefix and suffix.
That means, if the file name match, it will create new file with
".license" suffix that contains SPDX identifiers only, instead of
inserting to the file.

3 files changed, 93 insertions, 15 deletions

diff --git a/testdata/Apply_test.txt b/testdata/Apply_test.txt
index 712c2bc..43360b4 100644
--- a/testdata/Apply_test.txt
+++ b/testdata/Apply_test.txt
@@ -4,13 +4,48 @@
 // REUSE-IgnoreStart
 
 >>> spdxconv.cfg
-# SPDX-License-Identifier: BSD-3-Clause
+# SPDX-License-Identifier: CC0-1.0
 # SPDX-FileCopyrightText: 2026 M. Shulhan <ms@kilabit.info>
 
 [default]
 license_identifier = GPL-3.0-only
 file_copyright_text = M. Shulhan <ms@kilabit.info>
 
+[match-file-comment]
+pattern = "^.*\\.(adoc|asciidoc|c|cc|cpp|cs|dart|go|h|hh|hpp|java|js|jsx|jsonc|kt|kts|php|rs|sass|scss|swift|ts|tsx)$"
+prefix = "//"
+
+[match-file-comment]
+pattern = "^.*\\.(bash|csh|dockerfile|env|gitignore|hcl|ipynb|make|pl|pm|py|ps1|rb|sh|tf|yaml|yml|zsh)$"
+prefix = "#"
+
+[match-file-comment]
+pattern = "^.*\\.(css)$"
+prefix = "/*"
+suffix = "*/"
+
+[match-file-comment]
+pattern = "^.*\\.(fxml|htm|html|html5|kml|markdown|md|xml)$"
+prefix = "<!--"
+suffix = "-->"
+
+[match-file-comment]
+pattern = "^.*\\.(lua|sql)$"
+prefix = "--"
+
+[match-file-comment]
+pattern = "^.*\\.(rst)$"
+prefix = ".."
+
+[match-file-comment]
+pattern = "^.*\\.(tex)$"
+prefix = "%"
+
+# File name that match with this pattern will have the ".license" file
+# created.
+[match-file-comment]
+pattern = "^.*\\.(apk|app|bz2|csv|doc|docx|exe|gif|gz|jpeg|jpg|json|pdf|png|ppt|pptx|svg|svgz|tar|tgz|xls|xlsx|zip)$"
+
 [match-license]
 pattern = "^(//+|#+)\\s+(.*)governed by a BSD-style(.*)$"
 license_identifier = BSD-3-Clause
@@ -19,23 +54,26 @@ delete_line_pattern = "^(//+|#+)\\s+license that(.*)$"
 [match-copyright]
 pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<contact>.*)>.*$"
 
->>> without_spdx_license_id.txt
+>>> without_spdx_license_id.go
 1
 2
 3
 
-<<< without_spdx_license_id.txt
+<<< without_spdx_license_id.go
+// SPDX-License-Identifier: GPL-3.0-only
+// SPDX-FileCopyrightText: M. Shulhan <ms@kilabit.info>
+
 1
 2
 3
 
->>> with_spdx_at_bottom.txt
+>>> with_spdx_at_bottom.go
 1
 2
 3
 // SPDX-License-Identifier: GPL-3.0-only
 
-<<< with_spdx_at_bottom.txt
+<<< with_spdx_at_bottom.go
 // SPDX-License-Identifier: GPL-3.0-only
 // SPDX-FileCopyrightText: M. Shulhan <ms@kilabit.info>
 
@@ -43,13 +81,13 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
->>> with_spdx_license_id_only.txt
+>>> with_spdx_license_id_only.go
 // SPDX-License-Identifier: GPL-3.0-only
 1
 2
 3
 
-<<< with_spdx_license_id_only.txt
+<<< with_spdx_license_id_only.go
 // SPDX-License-Identifier: GPL-3.0-only
 // SPDX-FileCopyrightText: M. Shulhan <ms@kilabit.info>
 
@@ -57,7 +95,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
->>> with_spdx.txt
+>>> with_spdx.go
 // SPDX-License-Identifier: BSD-3-Clause
 // SPDX-FileCopyrightText: 2018 Shulhan <ms@kilabit.info>
 
@@ -65,7 +103,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
-<<< with_spdx.txt
+<<< with_spdx.go
 // SPDX-License-Identifier: BSD-3-Clause
 // SPDX-FileCopyrightText: 2018 Shulhan <ms@kilabit.info>
 
@@ -73,7 +111,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
->>> with_spdx_no_order.txt
+>>> with_spdx_no_order.go
 // SPDX-FileCopyrightText: 2026 M. Shulhan <ms@kilabit.info>
 // SPDX-License-Identifier: BSD-3-Clause
 
@@ -81,7 +119,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
-<<< with_spdx_no_order.txt
+<<< with_spdx_no_order.go
 // SPDX-FileCopyrightText: 2026 M. Shulhan <ms@kilabit.info>
 // SPDX-License-Identifier: BSD-3-Clause
 
@@ -89,7 +127,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
->>> with_match_license.txt
+>>> with_match_license.go
 // Copyright 2018, Shulhan <ms@kilabit.info>. All rights reserved.
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
@@ -98,7 +136,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
-<<< with_match_license.txt
+<<< with_match_license.go
 // SPDX-License-Identifier: BSD-3-Clause
 // SPDX-FileCopyrightText: 2018 Shulhan <ms@kilabit.info>
 
@@ -106,7 +144,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 2
 3
 
->>> with_match_license_bottom.txt
+>>> with_match_license_bottom.go
 1
 2
 3
@@ -115,7 +153,7 @@ pattern = "^(//+|#+)\\s+Copyright\\s+(?<year>\\d{4}),?\\s+(?<author>.*)\\s+<*(?<
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
-<<< with_match_license_bottom.txt
+<<< with_match_license_bottom.go
 // SPDX-License-Identifier: BSD-3-Clause
 // SPDX-FileCopyrightText: 2018 Shulhan <ms@kilabit.info>
 
diff --git a/testdata/Init/.gitignore b/testdata/Init/.gitignore
new file mode 100644
index 0000000..234c892
--- /dev/null
+++ b/testdata/Init/.gitignore
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-3.0-only
+// SPDX-FileCopyrightText: 2026 M. Shulhan <ms@kilabit.info>
+
+/*
+!/.gitignore
diff --git a/testdata/scan/spdxconv.cfg b/testdata/scan/spdxconv.cfg
index ec401a3..d317d64 100644
--- a/testdata/scan/spdxconv.cfg
+++ b/testdata/scan/spdxconv.cfg
@@ -6,6 +6,41 @@ license_identifier = GPL-3.0-only
 file_copyright_text = Author <contact@email.local>
 max_line_match = 10
 
+[match-file-comment]
+pattern = "^.*\\.(adoc|asciidoc|c|cc|cpp|cs|dart|go|h|hh|hpp|java|js|jsx|jsonc|kt|kts|php|rs|sass|scss|swift|ts|tsx)$"
+prefix = "//"
+
+[match-file-comment]
+pattern = "^.*\\.(aff|bash|csh|dockerfile|env|gitignore|hcl|ipynb|make|pl|pm|py|ps1|rb|sh|tf|yaml|yml|zsh)$"
+prefix = "#"
+
+[match-file-comment]
+pattern = "^.*\\.(css)$"
+prefix = "/*"
+suffix = "*/"
+
+[match-file-comment]
+pattern = "^.*\\.(fxml|htm|html|html5|kml|markdown|md|xml)$"
+prefix = "<!--"
+suffix = "-->"
+
+[match-file-comment]
+pattern = "^.*\\.(lua|sql)$"
+prefix = "--"
+
+[match-file-comment]
+pattern = "^.*\\.(rst)$"
+prefix = ".."
+
+[match-file-comment]
+pattern = "^.*\\.(tex)$"
+prefix = "%"
+
+# File name that match with this pattern will have the ".license" file
+# created.
+[match-file-comment]
+pattern = "^.*\\.(apk|app|bz2|csv|doc|docx|exe|gif|gz|jpeg|jpg|json|pdf|png|ppt|pptx|svg|svgz|tar|tgz|xls|xlsx|zip)$"
+
 [match-license]
 pattern = "^(//+|#+)\\s+(.*)governed by a BSD-style(.*)$"
 license_identifier = BSD-3-Clause