Vendor import of clang trunk r300422:vendor/clang/clang-trunk-r300422

https://llvm.org/svn/llvm-project/cfe/trunk@300422

3 files changed, 170 insertions, 19 deletions

diff --git a/tools/clang-format/ClangFormat.cpp b/tools/clang-format/ClangFormat.cpp
index 6c50daf53834..ac0d0a8512f4 100644
--- a/tools/clang-format/ClangFormat.cpp
+++ b/tools/clang-format/ClangFormat.cpp
@@ -236,8 +236,15 @@ static void outputReplacementsXML(const Replacements &Replaces) {
 
 // Returns true on error.
 static bool format(StringRef FileName) {
+  if (!OutputXML && Inplace && FileName == "-") {
+    errs() << "error: cannot use -i when reading from stdin.\n";
+    return false;
+  }
+  // On Windows, overwriting a file with an open file mapping doesn't work,
+  // so read the whole file into memory when formatting in-place.
   ErrorOr<std::unique_ptr<MemoryBuffer>> CodeOrErr =
-      MemoryBuffer::getFileOrSTDIN(FileName);
+      !OutputXML && Inplace ? MemoryBuffer::getFileAsStream(FileName) :
+                              MemoryBuffer::getFileOrSTDIN(FileName);
   if (std::error_code EC = CodeOrErr.getError()) {
     errs() << EC.message() << "\n";
     return true;
@@ -249,12 +256,18 @@ static bool format(StringRef FileName) {
   if (fillRanges(Code.get(), Ranges))
     return true;
   StringRef AssumedFileName = (FileName == "-") ? AssumeFileName : FileName;
-  FormatStyle FormatStyle =
+
+  llvm::Expected<FormatStyle> FormatStyle =
       getStyle(Style, AssumedFileName, FallbackStyle, Code->getBuffer());
+  if (!FormatStyle) {
+    llvm::errs() << llvm::toString(FormatStyle.takeError()) << "\n";
+    return true;
+  }
+
   if (SortIncludes.getNumOccurrences() != 0)
-    FormatStyle.SortIncludes = SortIncludes;
+    FormatStyle->SortIncludes = SortIncludes;
   unsigned CursorPosition = Cursor;
-  Replacements Replaces = sortIncludes(FormatStyle, Code->getBuffer(), Ranges,
+  Replacements Replaces = sortIncludes(*FormatStyle, Code->getBuffer(), Ranges,
                                        AssumedFileName, &CursorPosition);
   auto ChangedCode = tooling::applyAllReplacements(Code->getBuffer(), Replaces);
   if (!ChangedCode) {
@@ -264,7 +277,7 @@ static bool format(StringRef FileName) {
   // Get new affected ranges after sorting `#includes`.
   Ranges = tooling::calculateRangesAfterReplacements(Replaces, Ranges);
   bool IncompleteFormat = false;
-  Replacements FormatChanges = reformat(FormatStyle, *ChangedCode, Ranges,
+  Replacements FormatChanges = reformat(*FormatStyle, *ChangedCode, Ranges,
                                         AssumedFileName, &IncompleteFormat);
   Replaces = Replaces.merge(FormatChanges);
   if (OutputXML) {
@@ -291,9 +304,7 @@ static bool format(StringRef FileName) {
     Rewriter Rewrite(Sources, LangOptions());
     tooling::applyAllReplacements(Replaces, Rewrite);
     if (Inplace) {
-      if (FileName == "-")
-        errs() << "error: cannot use -i when reading from stdin.\n";
-      else if (Rewrite.overwriteChangedFiles())
+      if (Rewrite.overwriteChangedFiles())
         return true;
     } else {
       if (Cursor.getNumOccurrences() != 0)
@@ -334,10 +345,15 @@ int main(int argc, const char **argv) {
     cl::PrintHelpMessage();
 
   if (DumpConfig) {
-    std::string Config =
-        clang::format::configurationAsText(clang::format::getStyle(
+    llvm::Expected<clang::format::FormatStyle> FormatStyle =
+        clang::format::getStyle(
             Style, FileNames.empty() ? AssumeFileName : FileNames[0],
-            FallbackStyle));
+            FallbackStyle);
+    if (!FormatStyle) {
+      llvm::errs() << llvm::toString(FormatStyle.takeError()) << "\n";
+      return 1;
+    }
+    std::string Config = clang::format::configurationAsText(*FormatStyle);
     outs() << Config << "\n";
     return 0;
   }
diff --git a/tools/clang-format/clang-format-test.el b/tools/clang-format/clang-format-test.el
new file mode 100644
index 000000000000..0e1f4dde406b
--- /dev/null
+++ b/tools/clang-format/clang-format-test.el
@@ -0,0 +1,126 @@
+;;; clang-format-test.el --- unit tests for clang-format.el  -*- lexical-binding: t; -*-
+
+;; Copyright (C) 2017  Google Inc.
+
+;; Author: Philipp Stephani <phst@google.com>
+
+;; This file is distributed under the University of Illinois Open Source
+;; License.  See LICENSE.TXT for details.
+
+;;; Commentary:
+
+;; Unit tests for clang-format.el.
+
+;;; Code:
+
+(require 'clang-format)
+
+(require 'cl-lib)
+(require 'ert)
+(require 'pcase)
+
+(ert-deftest clang-format-buffer--buffer-encoding ()
+  "Tests that encoded text is handled properly."
+  (cl-letf* ((call-process-args nil)
+             ((symbol-function 'call-process-region)
+              (lambda (&rest args)
+                (push args call-process-args)
+                (pcase-exhaustive args
+                  (`(,_start ,_end ,_program ,_delete (,stdout ,_stderr)
+                             ,_display . ,_args)
+                   (with-current-buffer stdout
+                     (insert "<?xml version='1.0'?>
+<replacements xml:space='preserve' incomplete_format='false'>
+<replacement offset='4' length='0'> </replacement>
+<replacement offset='10' length='0'> </replacement>
+</replacements>
+"))
+                   0)))))
+    (with-temp-buffer
+      (let ((buffer-file-name "foo.cpp")
+            (buffer-file-coding-system 'utf-8-with-signature-dos)
+            (default-process-coding-system 'latin-1-unix))
+        (insert "ä =ö;\nü= ß;\n")
+        (goto-char (point-min))
+        (end-of-line)
+        (clang-format-buffer))
+      (should (equal (buffer-string) "ä = ö;\nü = ß;\n"))
+      (should (eolp))
+      (should (equal (buffer-substring (point) (point-max))
+                     "\nü = ß;\n")))
+    (should-not (cdr call-process-args))
+    (pcase-exhaustive call-process-args
+      (`((,start ,end ,_program ,delete (,_stdout ,_stderr) ,display . ,args))
+       (should-not start)
+       (should-not end)
+       (should-not delete)
+       (should-not display)
+       (should (equal args
+                      '("-output-replacements-xml" "-assume-filename" "foo.cpp"
+                        "-style" "file"
+                        ;; Beginning of buffer, no byte-order mark.
+                        "-offset" "0"
+                        ;; We have two lines with 2×2 bytes for the umlauts,
+                        ;; 1 byte for the line ending, and 3 bytes for the
+                        ;; other ASCII characters each.
+                        "-length" "16"
+                        ;; Length of a single line (without line ending).
+                        "-cursor" "7")))))))
+
+(ert-deftest clang-format-buffer--process-encoding ()
+  "Tests that text is sent to the clang-format process in the
+right encoding."
+  (cl-letf* ((hexdump (executable-find "hexdump"))
+             (original-call-process-region
+              (symbol-function 'call-process-region))
+             (call-process-inputs nil)
+             ;; We redirect the input to hexdump so that we have guaranteed
+             ;; ASCII output.
+             ((symbol-function 'call-process-region)
+              (lambda (&rest args)
+                (pcase-exhaustive args
+                  (`(,start ,end ,_program ,_delete (,stdout ,_stderr)
+                            ,_display . ,_args)
+                   (with-current-buffer stdout
+                     (insert "<?xml version='1.0'?>
+<replacements xml:space='preserve' incomplete_format='false'>
+</replacements>
+"))
+                   (let ((stdin (current-buffer)))
+                     (with-temp-buffer
+                       (prog1
+                           (let ((stdout (current-buffer)))
+                             (with-current-buffer stdin
+                               (funcall original-call-process-region
+                                        start end hexdump nil stdout nil
+                                        "-v" "-e" "/1 \"%02x \"")))
+                         (push (buffer-string) call-process-inputs)))))))))
+    (skip-unless hexdump)
+    (with-temp-buffer
+      (let ((buffer-file-name "foo.cpp")
+            (buffer-file-coding-system 'utf-8-with-signature-dos)
+            (default-process-coding-system 'latin-1-unix))
+        (insert "ä\n")
+        (clang-format-buffer))
+      (should (equal (buffer-string) "ä\n"))
+      (should (eobp)))
+    (should (equal call-process-inputs '("c3 a4 0a ")))))
+
+(ert-deftest clang-format-buffer--end-to-end ()
+  "End-to-end test for ‘clang-format-buffer’.
+Actually calls the clang-format binary."
+  (skip-unless (file-executable-p clang-format-executable))
+  (with-temp-buffer
+    (let ((buffer-file-name "foo.cpp")
+          (buffer-file-coding-system 'utf-8-with-signature-dos)
+          (default-process-coding-system 'latin-1-unix))
+      (insert "ä =ö;\nü= ß;\n")
+      (goto-char (point-min))
+      (end-of-line)
+      (clang-format-buffer))
+    (should (equal (buffer-string) "ä = ö;\nü = ß;\n"))
+    (should (eolp))
+    (should (equal (buffer-substring (point) (point-max))
+                   "\nü = ß;\n"))))
+
+;;; clang-format-test.el ends here
diff --git a/tools/clang-format/clang-format.el b/tools/clang-format/clang-format.el
index 0ac2da3ad29a..aa9c3ff4ca0b 100644
--- a/tools/clang-format/clang-format.el
+++ b/tools/clang-format/clang-format.el
@@ -95,9 +95,10 @@ of the buffer."
 (defun clang-format--replace (offset length &optional text)
   "Replace the region defined by OFFSET and LENGTH with TEXT.
 OFFSET and LENGTH are measured in bytes, not characters.  OFFSET
-is a zero-based file offset."
-  (let ((start (clang-format--filepos-to-bufferpos offset 'exact))
-        (end (clang-format--filepos-to-bufferpos (+ offset length) 'exact)))
+is a zero-based file offset, assuming ‘utf-8-unix’ coding."
+  (let ((start (clang-format--filepos-to-bufferpos offset 'exact 'utf-8-unix))
+        (end (clang-format--filepos-to-bufferpos (+ offset length) 'exact
+                                                 'utf-8-unix)))
     (goto-char start)
     (delete-region start end)
     (when text
@@ -130,11 +131,18 @@ is no active region.  If no style is given uses `clang-format-style'."
   (unless style
     (setq style clang-format-style))
 
-  (let ((file-start (clang-format--bufferpos-to-filepos start 'approximate))
-        (file-end (clang-format--bufferpos-to-filepos end 'approximate))
-        (cursor (clang-format--bufferpos-to-filepos (point) 'exact))
+  (let ((file-start (clang-format--bufferpos-to-filepos start 'approximate
+                                                        'utf-8-unix))
+        (file-end (clang-format--bufferpos-to-filepos end 'approximate
+                                                      'utf-8-unix))
+        (cursor (clang-format--bufferpos-to-filepos (point) 'exact 'utf-8-unix))
         (temp-buffer (generate-new-buffer " *clang-format-temp*"))
-        (temp-file (make-temp-file "clang-format")))
+        (temp-file (make-temp-file "clang-format"))
+        ;; Output is XML, which is always UTF-8.  Input encoding should match
+        ;; the encoding used to convert between buffer and file positions,
+        ;; otherwise the offsets calculated above are off.  For simplicity, we
+        ;; always use ‘utf-8-unix’ and ignore the buffer coding system.
+        (default-process-coding-system '(utf-8-unix . utf-8-unix)))
     (unwind-protect
         (let ((status (call-process-region
                        nil nil clang-format-executable
@@ -164,7 +172,8 @@ is no active region.  If no style is given uses `clang-format-style'."
               (dolist (rpl replacements)
                 (apply #'clang-format--replace rpl)))
             (when cursor
-              (goto-char (clang-format--filepos-to-bufferpos cursor 'exact)))
+              (goto-char (clang-format--filepos-to-bufferpos cursor 'exact
+                                                             'utf-8-unix)))
             (if incomplete-format
                 (message "(clang-format: incomplete (syntax errors)%s)" stderr)
               (message "(clang-format: success%s)" stderr))))