ack
e4f1307aa9
A character written in the ^...^ mnemonic form -- ^oe^, ^zz^, ^hello^ --
used to kill ktext outright: no message, no output, and an exit status
that looked like a crash because it was one. Only the forms that happen
to spell hexadecimal digits escaped, and they were right by luck rather
than by reading. Any caret form that names no character is now a located
error that quotes what was written.
A klammer may now sit inside square brackets and braces as it already
could inside parentheses, and may be followed by the punctuation that
ends a sentence: [@i word@], {@b word@}, @i word@'s. The rule is a fixed
list of characters, because none of them can occur inside a klammer name
and so none of them is ambiguous next to a delimiter. A letter still
cannot: "x@" is the named closing delimiter, so a letter before "@" has
two readings and no rule can separate them.
The abbreviations an author writes -- the hyphen form @i-word, a klammer
glued to its neighbouring punctuation -- are now recognised as author
conveniences only. They are not applied to @@ definitions or @@@ system
commands, which are written by someone who needs no such shorthand and
whose forms are already whole.
Also fixed, each of them silent: an exported shell function in the
environment broke every @eval in the document; a line break written with
@nl was destroyed when it passed through a klammer that generates a
table, printing as \textbackslash{}newline in the finished PDF; and
"kdesc --coverage" shortened its file column by comparing the spelling of
a path rather than the path, so a klammer set reached by a symbolic link
showed a full path where its neighbours showed a short one.
New in the distribution: ref/, a small klammerset that describes the
Klammermachine's own tables in Klammertext. It currently provides the
character tables -- the diacritics and the extended Latin letters -- as
klammers that render to any target, so the documentation of what can be
written cannot drift from what the machine accepts. It is early, and
will grow.
The Klammertext taxonomy now has a section on targets, describes the
@@@klammerset system command alongside the other three, and states the
precedence of "^" -- what a caret means before a letter, a digit, a
punctuation character, and a quote, in one ordered list.
(from dev 6594c7ff8c1f)
165 lines
6.5 KiB
C++
165 lines
6.5 KiB
C++
#pragma once
|
|
|
|
#include <string>
|
|
|
|
// #include "source.h"
|
|
#include "katom_process.h"
|
|
#include "klammer_registry.h"
|
|
#include "klammerset_registry.h"
|
|
#include "option_set_registry.h"
|
|
#include "target_registry.h"
|
|
#include "argtype_registry.h"
|
|
#include "state.h"
|
|
|
|
#include "error.h"
|
|
|
|
class Machine
|
|
{
|
|
public:
|
|
using input_sources_t =
|
|
std::vector<std::variant<fs::path, std::string>>;
|
|
|
|
Machine();
|
|
|
|
// Copy constructor
|
|
Machine(const Machine& other)
|
|
: m_argtypes(other.m_argtypes)
|
|
, m_state(other.m_state)
|
|
, m_targets(other.m_targets)
|
|
, m_klammers(other.m_klammers)
|
|
, m_klammersets(other.m_klammersets)
|
|
, m_option_sets(other.m_option_sets)
|
|
, m_result(other.m_result)
|
|
{}
|
|
|
|
// Copy assignment operator
|
|
Machine& operator=(const Machine& other) {
|
|
if (this != &other) {
|
|
m_argtypes = other.m_argtypes;
|
|
m_state = other.m_state;
|
|
m_targets = other.m_targets;
|
|
m_klammers = other.m_klammers;
|
|
m_klammersets = other.m_klammersets;
|
|
m_option_sets = other.m_option_sets;
|
|
m_result = other.m_result;
|
|
}
|
|
return *this;
|
|
}
|
|
|
|
// @cond is resolved at APPLICATION time, not read time (Andy, 2026-08-15,
|
|
// deciding notes/Klammertext_improvements.md §4.2). mark_cond_content()
|
|
// runs during process_katoms and makes every branch inert;
|
|
// resolve_cond_katoms() runs inside the apply fold, selects a branch, and
|
|
// processes only that one. The document then behaves like a klammer body:
|
|
// its state variables are bound before its conditionals are decided.
|
|
void mark_cond_content(std::vector<Katom>& katoms);
|
|
int resolve_cond_katoms(std::vector<Katom>& katoms, const std::string& target);
|
|
void process_eval_katoms(std::vector<Katom>& katoms);
|
|
void mark_literal_klammer_content(std::vector<Katom>& katoms);
|
|
void escape_target_characters(const Target& target, std::vector<Katom>& katoms);
|
|
|
|
// std::vector<Katom>
|
|
void process_katoms(
|
|
std::vector<Katom>& katoms, const std::string& source,
|
|
bool nonascii=true, bool literal=true, bool ignore=true, bool whitespace=true,
|
|
bool klammers=true, bool eval=true, bool cond=true, bool read=true);
|
|
|
|
std::vector<Katom> process(
|
|
std::string text, const std::string& source,
|
|
bool nonascii=true, bool literal=true, bool ignore=true, bool whitespace=true,
|
|
bool klammers=true, bool eval=true, bool cond=true, bool read=true);
|
|
|
|
void read(const fs::path& pathname);
|
|
void read(const std::string& s);
|
|
|
|
void expand_read_katoms(
|
|
std::vector<Katom>& katoms, std::string source_filename,
|
|
bool nonascii=true, bool literal=true, bool ignore=true, bool ws=true,
|
|
bool klammers=true, bool eval=true, bool cond=true, bool read=true);
|
|
|
|
void expand_constant_klammers(katom_list& katoms, const Katom& op, const Katom& cl);
|
|
void add_definition(katom_list& katoms, const Katom& op, const Katom& cl);
|
|
void load_klammerset_files(const Klammerset& klammerset, katom_iter insert_at);
|
|
// `tolerant` is for kdiag ONLY. It dissects the structure and typing of
|
|
// the katom list, and allows modes of processing that would be errors in
|
|
// ktext: run one definition tier without the other and a definition may
|
|
// be unregisterable (a klammer names a target that "--system" would have
|
|
// registered). Tolerant then SKIPS that definition instead of throwing,
|
|
// leaving its katoms unconsumed and therefore visible -- which is the
|
|
// report. ktext must keep throwing: there, a document naming an
|
|
// undefined target is a genuine error, and skipping it silently would
|
|
// render a wrong document.
|
|
void add_machine_definition(const std::string& name, katom_iter begin,
|
|
katom_iter end, bool& rescan);
|
|
void extract_machine_definitions(bool tolerant = false);
|
|
void extract_klammer_definitions(bool tolerant = false);
|
|
void extract_klammer_definitions(katom_list katoms);
|
|
void update_state(const std::map<std::string, std::string>& arg_map);
|
|
|
|
katom_list apply_klammer(Klammer& klammer, const std::string& target, katom_iter arguments_begin, katom_iter arguments_end);
|
|
|
|
void apply_klammer_registry(Klammer_registry& klammer_registry,
|
|
katom_list& katoms, const std::string& target, katom_iter begin, katom_iter end);
|
|
|
|
// Returns the number of klammers applied in this pass. The top-level
|
|
// fixed point loops while that count is nonzero: reduction is detected by
|
|
// a redex having been reduced, not by the katom list having grown.
|
|
int apply(Klammer_registry& klammer_registry, katom_list& katoms, const std::string& target);
|
|
|
|
std::string run_phase_functions();
|
|
std::string apply(const std::string& target_name, bool final_processing=true, bool escape_characters=true);
|
|
|
|
Argtype_registry m_argtypes {};
|
|
State m_state {};
|
|
Target_registry m_targets {};
|
|
Klammer_registry m_klammers {};
|
|
Klammerset_registry m_klammersets {};
|
|
Option_set_registry m_option_sets {};
|
|
input_sources_t m_sources {};
|
|
std::string m_result {};
|
|
std::vector<Katom> m_katoms {};
|
|
// False on the sub-Machine that re-reads an @eval result (Eval::eval):
|
|
// result text is machine-generated -- a renderer's raw target markup
|
|
// (e.g. a LaTeX column spec "@{}...") legitimately fails katom parsing
|
|
// and must not produce "Word not parsed" warnings.
|
|
bool m_warn_unparsed = true;
|
|
};
|
|
|
|
/*
|
|
class Machine {
|
|
private:
|
|
std::string m_name;
|
|
int m_id;
|
|
std::vector<std::string> m_sources;
|
|
bool m_active;
|
|
double m_value;
|
|
|
|
public:
|
|
// Default constructor
|
|
Machine() : m_name(""), m_id(0), m_sources(), m_active(false), m_value(0.0) {}
|
|
|
|
// Copy constructor
|
|
Machine(const Machine& other)
|
|
: m_name(other.m_name) // Copy name
|
|
, m_id(other.m_id) // Copy id
|
|
, m_sources() // Initialize m_sources as empty
|
|
, m_active(other.m_active) // Copy active status
|
|
, m_value(other.m_value) // Copy value
|
|
{
|
|
// m_sources is now empty, ready for new initialization
|
|
}
|
|
|
|
// Assignment operator (if needed)
|
|
Machine& operator=(const Machine& other) {
|
|
if (this != &other) {
|
|
m_name = other.m_name;
|
|
m_id = other.m_id;
|
|
m_sources.clear(); // Clear and leave empty
|
|
m_active = other.m_active;
|
|
m_value = other.m_value;
|
|
}
|
|
return *this;
|
|
}
|
|
};
|
|
*/
|