Verbatim-safe typography, ^-punctuation quoting, full-range ^UUUU^, polyglot html

Typographic transforms (---, quote pairs, ~) no longer touch verbatim
text: @c/@code/@source_listing content and ^'...'^ spans show exactly the
characters written. "^" before any punctuation character quotes it in
every target (the apostrophe excepted: ^' opens a literal span), with the
new :resolve option on @@@target declaring per-target renderings. The
^UUUU^ code-point form accepts 4-6 hex digits, the full Unicode range.
The html output and transform spellings are polyglot (XML-valid), in
preparation for an EPUB target. New suites: transform_test, character_test
(engine), typography_test (SKS).

(from dev 07ce5ea86a0a)

doc/edit/shared/klammertext_edit.py

@@ -36,10 +36,10 @@
 #   * the Emacs defcustoms (klammertext-literal-klammers, -transparent-,
 #     -code-, -align-klammers, -indent-offset, -align-cell-max, -align-row-max)
 #     in doc/edit/emacs/klammertext-mode.el / -indent.el / -align.el
-#   * the '@code' rule + literal_code context in
+#   * the '@code'/'@c' rules + literal_code/literal_c contexts in
 #     doc/edit/sublime/Klammertext.sublime-syntax
-#   * the '@code' verbatim region in doc/edit/vim/syntax/klammertext.vim
-#   * the '@code' rule in doc/edit/vscode/syntaxes/klammertext.tmLanguage.json
+#   * the '@code'/'@c' verbatim regions in doc/edit/vim/syntax/klammertext.vim
+#   * the '@code'/'@c' rules in doc/edit/vscode/syntaxes/klammertext.tmLanguage.json
 #
 # Installation note: editors locate this file either next to their own plugin
 # files (a vendored copy, placed there by doc/make_editing_zip.sh), as
@@ -57,7 +57,7 @@ import sys
 
 # Klammer names whose content is a literal argument (verbatim interior,
 # closed by a named NAME@ delimiter).
-LITERAL_KLAMMERS = set(["code"])
+LITERAL_KLAMMERS = set(["code", "c"])
 
 # Klammers that contribute no indentation level (a @document's paragraphs
 # stay at the left margin).
@@ -91,6 +91,19 @@ def name_char_p(ch):
             or ('0' <= ch <= '9') or ch == '_')
 
 
+def find_literal_close(s, name, start):
+    """Index of the exact close token NAME@ at or after START, or -1.
+    The engine's close is a whole katom, so NAME@ preceded by a name
+    character is content, not a close -- "basic@" does not close @c, and
+    "barcode@" does not close @code.  Single-letter literal names (@c) make
+    this guard essential rather than theoretical."""
+    close = name + '@'
+    idx = s.find(close, start)
+    while idx > 0 and name_char_p(s[idx - 1]):
+        idx = s.find(close, idx + 1)
+    return idx
+
+
 def escaped_p(s, pos):
     """True if the char at POS is escaped by an odd run of ^ before it.
     In Klammertext ^# and ^@ are literal, so such a char is not a delimiter."""
@@ -188,9 +201,8 @@ def next_app_delim(s, i, limit):
             name = s[hit + 1:k]
             after = s[k] if k < n else None
             if name in LITERAL_KLAMMERS:  # literal span: skip to its close
-                close = name + '@'
-                idx = s.find(close, k)
-                i = n if idx == -1 else idx + len(close)
+                idx = find_literal_close(s, name, k)
+                i = n if idx == -1 else idx + len(name) + 1
                 continue
             elif after == '-':           # @name-arg : opens no span
                 i = k
@@ -318,7 +330,7 @@ def literal_match_forward(s, open_pos, name):
     """Index of the @ of the NAME@ that closes the literal @NAME at OPEN_POS, or
     None.  The content is opaque, so search for the literal close string."""
     start = open_pos + 1 + len(name)
-    idx = s.find(name + '@', start)
+    idx = find_literal_close(s, name, start)
     return idx + len(name) if idx != -1 else None
 
 
@@ -333,7 +345,10 @@ def literal_match_backward(s, close_pos, name):
         if idx == -1:
             return None
         before = s[idx - 1] if idx > 0 else None
-        if before != '@' and not escaped_p(s, idx):
+        # The name must end where the token ends: "@c" found inside
+        # "@caption" is not an opener of @c.
+        follower = s[idx + len(open_str)] if idx + len(open_str) < len(s) else None
+        if before != '@' and not name_char_p(follower) and not escaped_p(s, idx):
             return idx
         end = idx
 
@@ -446,7 +461,7 @@ def state_at(s, pos):
             i = k
             if run_len == 1 and name in LITERAL_KLAMMERS:
                 # Verbatim interior: find the closing NAME@ by name.
-                idx = s.find(name + '@', k)
+                idx = find_literal_close(s, name, k)
                 if idx == -1:            # never closed
                     return (stack, True)
                 close_end = idx + len(name) + 1
@@ -584,7 +599,7 @@ def enclosing_span(s, pos, names):
             name = s[run_end:k]
             i = k
             if run_len == 1 and name in LITERAL_KLAMMERS:
-                idx = s.find(name + '@', k)
+                idx = find_literal_close(s, name, k)
                 if idx == -1:
                     break
                 i = idx + len(name) + 1
@@ -692,7 +707,7 @@ def scan_lines(content):
             name = content[run_end:k]
             i = k
             if run_len == 1 and name in LITERAL_KLAMMERS:
-                idx = content.find(name + '@', k)
+                idx = find_literal_close(content, name, k)
                 e = n if idx == -1 else idx + len(name) + 1
                 if line_index(max(hit, e - 1)) != line_index(hit):
                     block_range(hit, e)
@@ -886,7 +901,7 @@ def diagnostics(s):
             name = s[run_end:k]
             i = k
             if run_len == 1 and name in LITERAL_KLAMMERS:
-                idx = s.find(name + '@', k)
+                idx = find_literal_close(s, name, k)
                 if idx == -1:
                     probs.append({'start': hit, 'end': k,
                                   'message': ("literal klammer @%s has no "