From 30476493726d776d7ba79b4301d17563c91196b2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mikael=20L=C3=B6vqvist?= <mikael.lovqvist.mail@gmail.com>
Date: Mon, 4 May 2026 22:24:48 +0200
Subject: [PATCH] Work in progress on generic parser

---
 experiments/generic-parser-2.mjs | 136 +++++++++++++++++++++++++++++++
 source/table/table.mjs           |   8 ++
 2 files changed, 144 insertions(+)

diff --git a/experiments/generic-parser-2.mjs b/experiments/generic-parser-2.mjs
index e69de29..3f87f29 100644
--- a/experiments/generic-parser-2.mjs
+++ b/experiments/generic-parser-2.mjs
@@ -0,0 +1,136 @@
+import { Row_Based_Table } from '@efforting.tech/table';
+import { load_raster_table } from '@efforting.tech/table/raster-table';
+import { RegExp_Tokenizer } from '@efforting.tech/parsing/regexp-dispatch';
+import { RegExp_Token_Parsing_Rule, Parser } from '@efforting.tech/parsing/generic-parsing';
+
+
+function load_table(raster) {
+	const table = load_raster_table(raster, Row_Based_Table);
+	table.replace_all_cells(({cell}) => cell.trim());
+	return table;
+}
+
+const logic_ops = load_table(`
+
+	name		symbol
+	----		------
+	AND			∧
+	OR			∨
+	XOR			⊕
+	NAND		↑
+	NOR			↓
+	XNOR		⊙
+	IMPLIES		→
+	IFF			↔
+	NOT			¬
+
+`);
+
+const generic_ops = load_table(`
+
+	name		symbol
+	----		------
+	PLUS		+
+	HYPHEN		-
+	DOT			·
+	ASTERISK	*
+	CROSS		×
+	SLASH		/
+	CARET		^
+	UNDERSCORE	_
+	PERCENT		%
+
+`);
+
+const punctuation = load_table(`
+
+	name		symbol
+	----		------
+	COMMA		,
+	SEMI_COLON	;
+	COLON		:
+	PERIOD		.
+
+`);
+
+const grouping = load_table(`
+
+	name					left	right
+	----					----	-----
+	PARENTESIS				(		)
+	SQUARE_BRACKET			[		]
+	CURLY_BRACE				{		}
+	ANGLE_BRACKET			⟨		⟩
+	DOUBLE_ARROW_BRACKET	«		»
+
+`);
+
+const greek_chars = load_table(`
+
+	name		lower	upper
+	----		-----	-----
+	ALPHA		α		Α
+	BETA		β		Β
+	GAMMA		γ		Γ
+	DELTA		δ		Δ
+	EPSILON		ε		Ε
+	ZETA		ζ		Ζ
+	ETA			η		Η
+	THETA		θ		Θ
+	IOTA		ι		Ι
+	KAPPA		κ		Κ
+	LAMBDA		λ		Λ
+	MU			μ		Μ
+	NU			ν		Ν
+	XI			ξ		Ξ
+	OMICRON		ο		Ο
+	PI			π		Π
+	RHO			ρ		Ρ
+	SIGMA		σ		Σ
+	TAU			τ		Τ
+	UPSILON		υ		Υ
+	PHI			φ		Φ
+	CHI			χ		Χ
+	PSI			ψ		Ψ
+	OMEGA		ω		Ω
+
+`);
+
+
+
+const rt = new RegExp_Tokenizer();
+
+for (const { name, left, right } of grouping.iter_objects()) {
+	rt.add_rules(new RegExp_Token_Parsing_Rule(RegExp.escape(left),
+		(tokenizer, match) => tokenizer.enter_sub_tokenizer(undefined,
+			(tokenizer, value) => tokenizer.push_token(
+				{kind: 'grouping', name, value}
+			)
+		), `LEFT_${name}`
+	));
+
+	rt.add_rules(new RegExp_Token_Parsing_Rule(RegExp.escape(right),
+		(tokenizer, match) => tokenizer.leave_sub_tokenizer(), `RIGHT_${name}`)
+	);
+}
+
+
+for (const table of [logic_ops, generic_ops, punctuation]) {
+	for (const { name, symbol } of table.iter_objects()) {
+		rt.add_rules(new RegExp_Token_Parsing_Rule(RegExp.escape(symbol),
+			(tokenizer, match) => tokenizer.push_token(match.value), name)
+		);
+	}
+}
+
+for (const { name, lower, upper } of greek_chars.iter_objects()) {
+	rt.add_rules(new RegExp_Token_Parsing_Rule(RegExp.escape(lower),
+		(tokenizer, match) => tokenizer.push_token(match.value), `LOWER_${name}`)
+	);
+	rt.add_rules(new RegExp_Token_Parsing_Rule(RegExp.escape(upper),
+		(tokenizer, match) => tokenizer.push_token(match.value), `UPPER_${name}`)
+	);
+}
+
+
+console.log(rt.rules.at(-1));
\ No newline at end of file
diff --git a/source/table/table.mjs b/source/table/table.mjs
index 34d23f2..e963374 100644
--- a/source/table/table.mjs
+++ b/source/table/table.mjs
@@ -146,12 +146,20 @@ export class Row_Based_Table {
 	}
 
 
+	//TODO: Implement map and other functions expected by collections
+
 	*[Symbol.iterator]() {
 		for (const index of this.rows.keys()) {
 			yield new Table_Row_Reference(this, index);
 		}
 	}
 
+	*iter_objects() {
+		for (const index of this.rows.keys()) {
+			yield new Table_Row_Reference(this, index).object;
+		}
+	}
+
 
 }