Find a script's lexer from its shebang line

Scintillua's detect reads the first line as well as the name, and
without it hooks, bin scripts and anything else lacking an extension
stayed plain.

3 files changed, 16 insertions, 7 deletions

diff --git a/custom/extensions/syntax-highlight.lua b/custom/extensions/syntax-highlight.luaindex 2bff263..544fce1 100644--- a/custom/extensions/syntax-highlight.lua+++ b/custom/extensions/syntax-highlight.lua@@ -162,9 +162,11 @@ local function load_lexer_name(name) 	return nil end -local function lexer_for(name)+local function lexer_for(name, text) 	if type(scintillua.detect) == "function" then-		local ok, lang = pcall(scintillua.detect, name)+		-- The first line goes along, so a script with no extension is still+		-- known by its shebang.+		local ok, lang = pcall(scintillua.detect, name, text:match("^[^\n]*")) 		if ok and lang then 			local lexer = load_lexer_name(lang) 			if lexer then@@ -181,7 +183,7 @@ local function lexer_for(name) end  local function highlight(text)-	local lexer = lexer_for(filename)+	local lexer = lexer_for(filename, text) 	if not lexer then 		return nil 	end
diff --git a/custom/extensions/syntax-highlight.lua b/custom/extensions/syntax-highlight.lua
index 2bff263..544fce1 100644
--- a/custom/extensions/syntax-highlight.lua
+++ b/custom/extensions/syntax-highlight.lua
@@ -162,9 +162,11 @@ local function load_lexer_name(name)
 	return nil
 end
 
-local function lexer_for(name)
+local function lexer_for(name, text)
 	if type(scintillua.detect) == "function" then
-		local ok, lang = pcall(scintillua.detect, name)
+		-- The first line goes along, so a script with no extension is still
+		-- known by its shebang.
+		local ok, lang = pcall(scintillua.detect, name, text:match("^[^\n]*"))
 		if ok and lang then
 			local lexer = load_lexer_name(lang)
 			if lexer then
@@ -181,7 +183,7 @@ local function lexer_for(name)
 end
 
 local function highlight(text)
-	local lexer = lexer_for(filename)
+	local lexer = lexer_for(filename, text)
 	if not lexer then
 		return nil
 	end
diff --git a/tests/extensions/fake-lexers/lexer.lua b/tests/extensions/fake-lexers/lexer.luaindex adf7d5b..0632744 100644--- a/tests/extensions/fake-lexers/lexer.lua+++ b/tests/extensions/fake-lexers/lexer.lua@@ -1,9 +1,9 @@ -- A miniature stand-in for the Scintillua lexer module, just enough for the -- syntax-highlight checks to drive every path through the filter without the -- real collection installed. load() hands out one of the toy lexers below by--- name and detect() recognises a single filename suffix, so a check can tell--- the detection path apart from the extension path by which lexer ends up--- running. Anything the filter treats as optional, a lexer that will not+-- name and detect() recognises a single filename suffix or a shebang naming+-- fake, so a check can tell the detection path apart from the extension path+-- by which lexer ends up running. Anything the filter treats as optional, a lexer that will not -- load or one that raises while lexing, has a name here too.  local M = {}@@ -67,10 +67,13 @@ function M.load(name) 	return lexer end -function M.detect(filename)+function M.detect(filename, line) 	if filename:match("%.viadetect$") then 		return "fake" 	end+	if line ~= nil and line:match("^#!.*fake") then+		return "fake"+	end 	return nil end 
diff --git a/tests/extensions/fake-lexers/lexer.lua b/tests/extensions/fake-lexers/lexer.lua
index adf7d5b..0632744 100644
--- a/tests/extensions/fake-lexers/lexer.lua
+++ b/tests/extensions/fake-lexers/lexer.lua
@@ -1,9 +1,9 @@
 -- A miniature stand-in for the Scintillua lexer module, just enough for the
 -- syntax-highlight checks to drive every path through the filter without the
 -- real collection installed. load() hands out one of the toy lexers below by
--- name and detect() recognises a single filename suffix, so a check can tell
--- the detection path apart from the extension path by which lexer ends up
--- running. Anything the filter treats as optional, a lexer that will not
+-- name and detect() recognises a single filename suffix or a shebang naming
+-- fake, so a check can tell the detection path apart from the extension path
+-- by which lexer ends up running. Anything the filter treats as optional, a lexer that will not
 -- load or one that raises while lexing, has a name here too.
 
 local M = {}
@@ -67,10 +67,13 @@ function M.load(name)
 	return lexer
 end
 
-function M.detect(filename)
+function M.detect(filename, line)
 	if filename:match("%.viadetect$") then
 		return "fake"
 	end
+	if line ~= nil and line:match("^#!.*fake") then
+		return "fake"
+	end
 	return nil
 end
 
diff --git a/tests/extensions/test-syntax-highlight.lua b/tests/extensions/test-syntax-highlight.luaindex a9e8b36..a87cd80 100644--- a/tests/extensions/test-syntax-highlight.lua+++ b/tests/extensions/test-syntax-highlight.lua@@ -60,6 +60,10 @@ h.equals("a lexer that raises falls back to escaped text", out, "some &lt;code&g out = render("script.viadetect", "if") h.equals("filename detection picks the lexer", out, "<span class='hl-keyword'>if</span>") +out = render("post-receive", "#!/usr/bin/fake\nif")+h.contains("a shebang picks the lexer of a file with no extension", out,+	"<span class='hl-keyword'>if</span>")+ out = render("tool.py", "import <x>") h.equals("an extension with no lexer serves escaped text", out, "import &lt;x&gt;") 
diff --git a/tests/extensions/test-syntax-highlight.lua b/tests/extensions/test-syntax-highlight.lua
index a9e8b36..a87cd80 100644
--- a/tests/extensions/test-syntax-highlight.lua
+++ b/tests/extensions/test-syntax-highlight.lua
@@ -60,6 +60,10 @@ h.equals("a lexer that raises falls back to escaped text", out, "some &lt;code&g
 out = render("script.viadetect", "if")
 h.equals("filename detection picks the lexer", out, "<span class='hl-keyword'>if</span>")
 
+out = render("post-receive", "#!/usr/bin/fake\nif")
+h.contains("a shebang picks the lexer of a file with no extension", out,
+	"<span class='hl-keyword'>if</span>")
+
 out = render("tool.py", "import <x>")
 h.equals("an extension with no lexer serves escaped text", out, "import &lt;x&gt;")