kdesc --rewrite from the reflection klammerset; txt caption rules the block's width

Assembled from klammertext-dev e99530408517. The katom rewrite patterns
are rendered from ref/ (a table in dispatch order, patterns through @c),
the procedural listing having left mac/; a plain-text caption's rule is
as long as the table or listing it captions; the editor-support comments
name the tools' new dev/ location.

README.md

@@ -51,7 +51,7 @@ are regenerated on each release — patches cannot be merged directly.
 Report problems (or send patches) to the author; accepted changes are
 applied to the development tree and appear in a following snapshot.
 
-This snapshot was assembled from development commit `e727ce1d248d`.
+This snapshot was assembled from development commit `e99530408517`.
 
 ## License
 

com/kdesc.cpp

@@ -201,6 +201,13 @@ void describe_katoms(bool show_regex)
     std::cout << "\n" << M.apply(text_target()) << "\n\n";
 }
 
+void show_katom_rewrite_patterns()
+{
+    Machine M = ref_machine();
+    M.read_string("@katom_rewrite_patterns@");
+    std::cout << "\n" << M.apply(text_target()) << "\n\n";
+}
+
 int main(int argc, char* argv[])
 {
     try {
@@ -269,7 +276,7 @@ int main(int argc, char* argv[])
         }
 
         if (p("rewrite")) {
-            describe_rewrite_patterns();
+            show_katom_rewrite_patterns();
         }
 
         // The --typeface subcommands operate on the Klammertext font store

doc/edit/README.md

@@ -75,7 +75,7 @@ Two kinds of artifact cannot read it and restate parts of it by hand:
 
 ## Testing
 
-`tst/editor_test.sh` (run by `dbg/rebuild.sh` and `make -C tst test`)
+`tst/editor_test.sh` (run by `dev/rebuild.sh` and `make -C tst test`)
 drives the fixture pairs in `tst/editor/` through the shared core's API
 and CLI, checks idempotence, checks the Emacs implementation for
 byte-equality, runs the language server through a scripted LSP client

doc/edit/shared/klammertext_edit.py

@@ -42,7 +42,7 @@
 #   * 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
+# files (a vendored copy, placed there by dev/make_editing_zip.sh), as
 # ../shared/klammertext_edit.py relative to the plugin directory (the layout
 # of this repository), or under $KLAMMERTEXT_HOME/doc/edit/shared/.
 #

doc/edit/sublime/Klammertext.py

@@ -27,7 +27,7 @@
 # policy list.  This file is only the Sublime wrapper.
 #
 # The shared core is located next to this file (a vendored copy — the
-# installed-package layout produced by doc/make_editing_zip.sh), or in
+# installed-package layout produced by dev/make_editing_zip.sh), or in
 # ../shared (the repository layout), or under $KLAMMERTEXT_HOME.
 #
 # SYNC: the literal-klammer set in the shared core must agree with the @code

doc/edit/sublime/Klammertext_align.py

@@ -23,7 +23,7 @@
 # Sublime command wrapper.
 #
 # The shared core is located next to this file (a vendored copy — the
-# installed-package layout produced by doc/make_editing_zip.sh), or in
+# installed-package layout produced by dev/make_editing_zip.sh), or in
 # ../shared (the repository layout), or under $KLAMMERTEXT_HOME.
 
 import os

doc/edit/sublime/Klammertext_indent.py

@@ -18,7 +18,7 @@
 # the language server.  This file is only the Sublime command wrapper.
 #
 # The shared core is located next to this file (a vendored copy — the
-# installed-package layout produced by doc/make_editing_zip.sh), or in
+# installed-package layout produced by dev/make_editing_zip.sh), or in
 # ../shared (the repository layout), or under $KLAMMERTEXT_HOME.
 
 import os

env/makefile.env

@@ -18,7 +18,7 @@ UNAME_S     := $(shell uname -s)
 CPP_VERSION := c++20
 # Default compiler: clang on macOS, gcc elsewhere. gcc-built Klammertext
 # binaries crash at runtime on macOS (a documented gcc/macOS codegen issue), so
-# gcc there is only a compile-time conformance check (via `./dbg/rebuild.sh
+# gcc there is only a compile-time conformance check (via `./dev/rebuild.sh
 # gcc`, which compiles under g++ then rebuilds with clang). Override with
 # `make COMPILER=...`.
 ifeq ($(UNAME_S),Darwin)

kpy/Makefile

@@ -4,7 +4,7 @@
 # Like ref/reflect.so and sks/document/document.so it links against
 # libklammertext.so and shares the engine's class layouts, so it is rebuilt
 # whenever they are (mac/Makefile's "all" runs "make -C kpy"; com/Makefile's
-# "redo" and dbg/rebuild.sh clean it -- a clean that misses a directory is a
+# "redo" and dev/rebuild.sh clean it -- a clean that misses a directory is a
 # mixed-object hazard, not a tidiness one).
 #
 # The module's filename carries the interpreter's ABI tag

mac/eval_python.cpp

@@ -261,7 +261,7 @@ std::string Eval_python::eval(std::string code)
     (void)K::log(3, code);
     code = m_machine.m_state.subst(code, true);
     // Kept as a record of a value worth watching; line comments rather than a
-    // block, so the msg() guard can see it is inert (doc/check_output_policy.sh
+    // block, so the msg() guard can see it is inert (dev/check_output_policy.sh
     // is line-based and cannot tell it is inside a /* */).
     // msg() << "\n"
     //  << std::string(80, '-') << "\n"

mac/katom_rewrite_rules.cpp

@@ -321,61 +321,3 @@ bool category_order_holds(const std::string& word, std::string& why, rewrite_ord
     }
     return true;
 }
-
-void describe_rewrite_patterns()
-{
-    if (verbose_level > 0) {
-        std::string desc_text = "doc/katom_patterns.desc";
-        std::cout << "\n"
-                  << justify(string_from_file(klammertext_filename(desc_text)))
-                  << "\n\n";
-    }
-    size_t width0 = 0;
-    size_t width1 = 0;
-    size_t width2 = 0;
-    for (const Rewrite_rule& rule : rewrite_rules) {
-        width0 = std::max(width0, category_name(rule.category).size());
-        width1 = std::max(width1, rule.description.size());
-        width2 = std::max(width2, rule.pattern.m_pattern.size());
-    }
-    width0 += 2;
-    width1 += 2;
-    width2 += 2;
-
-    std::cout << boldblack << std::setfill(' ')
-              << std::setw(width0) << std::left << "  Category"
-              << std::setw(width1) << std::left << "Description"
-              << std::setw(width2) << std::left << "Pattern"
-              << "Replacement" << black << "\n";
-
-    // Dispatch order, not declaration order: what a reader needs is the
-    // sequence the rules are actually TRIED in, since that is what decides
-    // which one fires.
-    rule_category shown {};
-    bool first = true;
-    for (size_t i : rule_order(rewrite_order::by_category)) {
-        const Rewrite_rule& rule = rewrite_rules[i];
-        std::string category = category_name(rule.category);
-        if (first || rule.category != shown) {
-            shown = rule.category;
-            first = false;
-        } else {
-            category = "";              // name a category once, at its head
-        }
-        std::string desc = rule.description;
-        desc[0] = static_cast<char>(toupper(desc[0]));
-        std::cout << "  "
-                  << std::left
-                  << std::setw(width0) << category
-                  << std::setw(width1) << desc
-                  << std::setw(width2) << rule.pattern.m_pattern
-                  << (rule.special ? "(not a pattern replacement)" : rule.replacement)
-                  << "\n";
-    }
-    if (verbose_level > 0) {
-        std::string notes_text = "doc/katom_patterns.notes";
-        std::cout << "\n\n"
-                  << justify(string_from_file(klammertext_filename(notes_text)))
-                  << "\n\n";
-    }
-}

mac/katom_rewrite_rules.h

@@ -142,9 +142,3 @@ std::vector<size_t> matching_rules(const std::string& word, rewrite_order order
 // state an invariant across.
 bool category_order_holds(const std::string& word, std::string& why,
                           rewrite_order order = rewrite_order::by_category);
-
-// The "kdesc --rewrite" listing.  It moved here with the table it reads,
-// and gained the CATEGORY column -- which is the point of the categories
-// reaching the user rather than only the maintainer: a reader sees the nine
-// groups and their order instead of thirty positions.
-void describe_rewrite_patterns();

ref/ref.k

@@ -48,3 +48,10 @@
 
 @@katom_descriptions.* ::
   @eval :cpp *KLAMMERTEXT_HOME*/ref/reflect katom_descriptions @ @@
+
+@@katom_rewrite_patterns.k :
+  Show the rewrite patterns for parsed text that is not a katom @@
+
+@@katom_rewrite_patterns.* ::
+  @eval :cpp *KLAMMERTEXT_HOME*/ref/reflect katom_rewrite_patterns @ @@
+

ref/reflect.cpp

@@ -194,6 +194,24 @@ std::string argtype_definitions(Machine& machine)
 }
 
 
+// Verbatim text as a table cell: a regex, a replacement string.  It goes
+// through @c, whose literal content is exempt from every special (a bar, a
+// hash, an at sign) -- but a literal value has its caret forms processed as
+// it is built, so a caret is written quoted: bare, "[^^@#|]+" would display
+// as "[^@#|]+" and "[@|#^:*]" would lose its caret to the colon.  The
+// exception is a caret before an apostrophe: "^'" is not a quoting form (it
+// opens a literal span elsewhere) and passes through as written.
+static std::string code_cell(const std::string& text)
+{
+    std::string quoted {};
+    for (size_t i = 0; i < text.size(); i++) {
+        const char c = text[i];
+        const bool before_apostrophe = i + 1 < text.size() && text[i + 1] == '\'';
+        quoted += (c == '^' && !before_apostrophe) ? "^^" : std::string(1, c);
+    }
+    return "@c :nd | " + quoted + " c@";
+}
+
 // The Regex cell of a katom type.  A type the Machine assigns is matched by
 // no regex and its cell is empty -- ws_added among them, whose m_pattern is a
 // description and not a regex (see the note in mac/katom_matching.cpp).  The
@@ -209,18 +227,7 @@ static std::string katom_regex_cell(const Ktype& k)
     if (k.m_type == katom_t::newline) {
         return "@t \\n @";
     }
-    // A literal value has its caret forms processed as it is built, so a
+    return code_cell(k.m_pattern);
-    // caret is written quoted: bare, "[^^@#|]+" would display as "[^@#|]+"
-    // and "[@|#^:*]" would lose its caret to the colon.
-    // The exception is a caret before an apostrophe: "^'" is not a quoting
-    // form (it opens a literal span elsewhere) and passes through as written.
-    std::string quoted {};
-    for (size_t i = 0; i < k.m_pattern.size(); i++) {
-        const char c = k.m_pattern[i];
-        const bool before_apostrophe = i + 1 < k.m_pattern.size() && k.m_pattern[i + 1] == '\'';
-        quoted += (c == '^' && !before_apostrophe) ? "^^" : std::string(1, c);
-    }
-    return "@c :nd | " + quoted + " c@";
 }
 
 extern "C"
@@ -290,3 +297,41 @@ characters can be displayed by the @t-kdesc command: @t kdesc -c -u @
     kt << rows.str() << "table@\n";
     return kt.str();
 }
+
+
+extern "C"
+std::string katom_rewrite_patterns([[maybe_unused]] Machine& machine)
+{
+    std::stringstream kt {};
+    kt << "@s2 Katom rewrite patterns @\n\n"
+       << R"(The table lists how a text is reformed or split into one or more katoms.
+ @i [Need a longer description here.] @
+
+)"
+       << "@table :caption The rewriting patterns for elements that are not katoms | "
+       << "Category | Description | Pattern | Replacement ||\n";
+
+    // Dispatch order, not declaration order: what a reader needs is the
+    // sequence the rules are actually TRIED in, since that is what decides
+    // which one fires.
+    rule_category shown {};
+    bool first = true;
+    std::string b = " | ";
+    for (size_t i : rule_order(rewrite_order::by_category)) {
+        const Rewrite_rule& rule = rewrite_rules[i];
+        std::string category = category_name(rule.category);
+        if (first || rule.category != shown) {
+            shown = rule.category;
+            first = false;
+        } else {
+            category = "";              // name a category once, at its head
+        }
+        std::string desc = rule.description;
+        desc[0] = static_cast<char>(toupper(desc[0]));
+        kt << category << b << desc << b << code_cell(rule.pattern.m_pattern) << b
+           << (rule.special ? "(hyphens separate word arguments)" : code_cell(rule.replacement))
+           << " ||\n";
+    }
+    kt << "table@\n";
+    return kt.str();
+}

sks/target/phases.py

@@ -244,10 +244,29 @@ def txt_insert_captions(text, K):
     # "Listing 1", not "Listing 2".  It was one counter for every label.
     caption_numbers = {}
     width = int(K.Target_txt_width)
+    verbatim = txt_verbatim_marker()
+    def block_width(lines):
+        # The visible width of the laid-out block adjacent to a caption:
+        # its lines carry the verbatim marker, and the first line that does
+        # not (or a blank line) ends the block.
+        widest = 0
+        for line in lines:
+            if not line.startswith(verbatim) or not line.strip():
+                break
+            widest = max(widest, txt_visible_length(line))
+        return widest
     def replace(m):
         indent_run, name, text = m.groups()
         indent = len(indent_run) // len(nbsp)
         indented_width = max(1, width - indent)
+        # The block the caption belongs to: below a top caption, above a
+        # bottom one.  Its width is what the caption's rule is drawn to,
+        # so the rule under "Table 1 - Prices" is as long as the table's
+        # own rules, not as long as those words.  (Before the match sits
+        # the caption line's own verbatim marker: drop that line.)
+        after = m.string[m.end():].split("\n")[1:]
+        before = m.string[:m.start()].split("\n")[:-1]
+        block = max(block_width(after), block_width(reversed(before)))
         # An empty label means an unnumbered caption (":number false").  It
         # must NOT take a number from the sequence: a reader counting the
         # captions they can see would then find the next one a number
@@ -263,6 +282,7 @@ def txt_insert_captions(text, K):
         if txt_visible_length(caption) > indented_width:
             lines = txt_wrap(caption, indented_width)
         line_length = max(txt_visible_length(e) for e in lines)
+        line_length = max(line_length, block - indent)
         lines.append("-" * line_length)
         lead = txt_verbatim_marker() + indent_run
         # The first line's marker is already in the text, before the indent