Files
klammertext/mac/util.h

122 lines
5.1 KiB
C
Raw Normal View History

#pragma once
#include <vector>
#include <string>
#include <regex>
#include <mutex>
#include <map>
#include <memory>
#include <functional>
#include <tuple>
#include <utility>
#include <algorithm>
inline std::mutex env_mutex;
class Katom;
using strings_t = std::vector<std::string>;
using string_pairs = std::vector<std::pair<std::string, std::string>>;
using string_map = std::map<std::string, std::string>;
using katom_ptr = std::shared_ptr<Katom>;
using katom_list = std::vector<Katom>;
using katom_lists = std::vector<katom_list>;
using katom_list_map = std::map<std::string, katom_list>;
using katom_iter = katom_list::iterator;
using spans_t = std::vector<std::pair<Katom, Katom>>;
using argument_value_map = std::map<std::string, std::string>;
std::string trim_left(const std::string& s);
std::string trim_right(const std::string& s);
std::string trim(std::string s);
std::string trim_char_left(std::string s, char remove);
std::string trim_char_right(std::string s, char remove);
std::string trim_char(std::string s, char remove);
std::string string_replace(const std::string& source, const std::string& old_str, const std::string& new_str);
std::string regex_escape(const std::string& s);
bool contains(const std::string& str, const std::string& substr);
bool contains(const std::vector<std::string>& strings, const std::string& element);
std::vector<std::string> regex_split(const std::string& s, const std::regex& re, bool trim_parts=true);
std::vector<std::string> word_split(const std::string& s);
Target coverage: a klammer states the targets it serves kdesc gains --coverage, which reports for every klammer the set of targets it can render to, and — the point of it — which klammers' coverage cannot be derived and must therefore be declared. Three rules: coverage is DERIVED where the definitions determine it (a general body of klammer calls covers the intersection of what those klammers cover, by a greatest fixpoint after loading), DECLARED where the engine cannot interpret what decides it (an @eval body, whose targets are undecidable), and UNKNOWN where nothing is written — which never means "deliberately unavailable". Two new spellings in a definition's name. A comma-separated target list, "@@table.html,tex :: ...", gives one body several targets; it is surface syntax, expanded at registration, and each member goes through the redefinition rules on its own. And "@@date.* :: ..." writes the general target out, asserting that the klammer works for EVERY target including ones not yet defined — a stronger claim than a list of the targets defined today, and the one target declaration that could be mechanically falsified. The Standard Klammer Set was swept accordingly: it now has no general definitions at all, every klammer names the targets it serves, six use ".*", and tex and pdf are at zero undecided. kdesc's flags are reorganised on two rules: a flag reached for often gets a single letter (-k klammers, -t targets, -c characters, -i input), a more specialised topic a multi-letter name (--argtypes, --katoms, --rewrite, --optionsets, --coverage, --klammerset, --font); and -v says how much to show about PROCESSING, never what the RESULT contains — so the katom regex column is "--katoms full" and the coverage detail "--coverage all". NOTE: "-k" now lists klammers (optionally filtered by a name/description search); the katom table moved to "--katoms". Fixes carried along: an option written with no value crashed the command with SIGSEGV instead of reporting the mistake; two required positional arguments never parsed; kdesc and kdiag printed an error and exited 0; and definition diagnostics counted registrations rather than what was written, so one line could be reported as two definitions and then printed twice. Four new test suites: target_list, coverage, command_option, kdesc. (from dev 46f54080bd9a)
2026-08-12 17:20:23 +02:00
// Every run of whitespace becomes one space, and the ends are trimmed. Needed
// wherever a phrase typed on one line is matched against text that was written
// across several: a klammer's description sits on its own lines in a ".k" file
// and may wrap, so "displayed verbatim" would otherwise match the klammer
// whose description happens to fit one line and miss the identically worded
// one that does not.
std::string collapse_whitespace(const std::string& s);
// Case-insensitive substring test, ASCII folding only. The project takes no
// ICU or locale dependency (the same rule as the language tables and
// ":decimal"), so a non-ASCII query matches only exactly.
bool contains_fold(const std::string& haystack, const std::string& needle);
bool is_in(const std::string& s, const std::vector<std::string>& v);
bool is_not_in(const std::string& s, const std::vector<std::string>& v);
std::vector<std::string> find_all(const std::string& str, const std::regex& pattern, int match_group=0);
std::vector<std::string> find_all(const std::string& str, const std::string& pattern, int match_group=0);
std::string add_margin(const std::string& s, unsigned int margin_size);
std::string justify(const std::string& input_text, unsigned int text_width=80, unsigned int margin_width=0);
std::string join(const std::vector<std::string>& ss, const std::string& separator = " ");
std::string join(int argc, char* array[], const std::string& separator = " ");
std::string argv_to_string(int argc, char* argv[]);
std::string plural(const std::string& word, int count);
std::string plural(const std::string& word, const std::vector<std::string>& things);
std::string to_be(int count, bool present = true);
int max_length(const std::vector<std::string>& ss);
std::vector<std::pair<std::string, std::string>> environment_variables(bool allow_empty_definitions=true);
std::string replace_environment_variables(const std::string& str);
std::string abbrev(const std::string& s, unsigned int max_length=65, bool remove_newlines=true);
void remove_element(std::vector<std::string>& ss, const std::string& removed);
void remove_duplicates(std::vector<std::string>& ss);
std::string display_string(const std::string& s, unsigned int width=40, bool replace_newlines=true);
std::pair<std::string,std::string> extract_parameter_type(const std::string& parameter_name);
std::tuple<std::string, std::string, bool> regex_split_prefix(const std::regex& pattern, const std::string& text);
std::vector<std::string> dlist_split(const std::string& s);
std::string get_env_var(const std::string& var);
std::string freplace(const std::string& src, const std::regex& pattern,
const std::function<std::string(std::smatch)>& func);
std::string exec(const char* cmd);
inline std::string q_(const std::string& s)
{
return "\"" + s + "\"";
}
inline std::string qq_(const std::string& s)
{
if (s.find('\n') == std::string::npos) {
return "\"" + s + "\"";
} else {
return "\"\"\"" + s + "\"\"\"";
}
}
template <typename T, typename Pred>
std::vector<T> collect_if(const std::vector<T>& xs, Pred pred) {
std::vector<T> out;
out.reserve(xs.size());
for (const auto& v : xs) {
if (pred(v)) out.push_back(v);
}
out.shrink_to_fit();
return out;
}
template <typename T>
bool all_equal(const std::vector<T>& v) {
if (v.size() < 2) return true;
return std::adjacent_find(v.begin(), v.end(), std::not_equal_to<T>{}) == v.end();
}
template <typename T>
int max_key_length(const std::map<std::string, T>& map)
{
size_t result = 0;
for_each(map.begin(), map.end(),
[&result](const auto& item) { result = std::max(result, item.first.size()); });
return result;
}