From c18cdb6998c488c92d5e62448f7db3eebcae7d99 Mon Sep 17 00:00:00 2001
From: zfletch <zfletch2@gmail.com>
Date: Fri, 30 Apr 2021 10:36:47 -0400
Subject: [PATCH 1/3] support aditional order for beta code to unicode

Add support for the following order:
On uppercase letters these are keyed in the order: (1) asterisk, (2) breathing, (3) accent, (4) letter, (5) iota subscript. E.g. *(=W|

This is the order specified in the [TLG manual web
page](http://stephanus.tlg.uci.edu/encoding.php).
---
 beta_code_to_unicode.json | 48 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/beta_code_to_unicode.json b/beta_code_to_unicode.json
index 7501955..7749eff 100644
--- a/beta_code_to_unicode.json
+++ b/beta_code_to_unicode.json
@@ -17,11 +17,17 @@
   "*(/u": "Ὕ",
   "*(/w": "Ὥ",
   "*(/|A": "ᾍ",
+  "*(/A|": "ᾍ",
   "*(/|H": "ᾝ",
+  "*(/H|": "ᾝ",
   "*(/|W": "ᾭ",
+  "*(/W|": "ᾭ",
   "*(/|a": "ᾍ",
+  "*(/a|": "ᾍ",
   "*(/|h": "ᾝ",
+  "*(/h|": "ᾝ",
   "*(/|w": "ᾭ",
+  "*(/w|": "ᾭ",
   "*(=A": "Ἇ",
   "*(=H": "Ἧ",
   "*(=I": "Ἷ",
@@ -33,11 +39,17 @@
   "*(=u": "Ὗ",
   "*(=w": "Ὧ",
   "*(=|A": "ᾏ",
+  "*(=A|": "ᾏ",
   "*(=|H": "ᾟ",
+  "*(=H|": "ᾟ",
   "*(=|W": "ᾯ",
+  "*(=W|": "ᾯ",
   "*(=|a": "ᾏ",
+  "*(=a|": "ᾏ",
   "*(=|h": "ᾟ",
+  "*(=h|": "ᾟ",
   "*(=|w": "ᾯ",
+  "*(=w|": "ᾯ",
   "*(A": "Ἁ",
   "*(E": "Ἑ",
   "*(H": "Ἡ",
@@ -61,11 +73,17 @@
   "*(\\u": "Ὓ",
   "*(\\w": "Ὣ",
   "*(\\|A": "ᾋ",
+  "*(\\A|": "ᾋ",
   "*(\\|H": "ᾛ",
+  "*(\\H|": "ᾛ",
   "*(\\|W": "ᾫ",
+  "*(\\W|": "ᾫ",
   "*(\\|a": "ᾋ",
+  "*(\\a|": "ᾋ",
   "*(\\|h": "ᾛ",
+  "*(\\h|": "ᾛ",
   "*(\\|w": "ᾫ",
+  "*(\\w|": "ᾫ",
   "*(a": "Ἁ",
   "*(e": "Ἑ",
   "*(h": "Ἡ",
@@ -75,11 +93,17 @@
   "*(u": "Ὑ",
   "*(w": "Ὡ",
   "*(|A": "ᾉ",
+  "*(A|": "ᾉ",
   "*(|H": "ᾙ",
+  "*(H|": "ᾙ",
   "*(|W": "ᾩ",
+  "*(W|": "ᾩ",
   "*(|a": "ᾉ",
+  "*(a|": "ᾉ",
   "*(|h": "ᾙ",
+  "*(h|": "ᾙ",
   "*(|w": "ᾩ",
+  "*(w|": "ᾩ",
   "*)/A": "Ἄ",
   "*)/E": "Ἔ",
   "*)/H": "Ἤ",
@@ -93,11 +117,17 @@
   "*)/o": "Ὄ",
   "*)/w": "Ὤ",
   "*)/|A": "ᾌ",
+  "*)/A|": "ᾌ",
   "*)/|H": "ᾜ",
+  "*)/H|": "ᾜ",
   "*)/|W": "ᾬ",
+  "*)/W|": "ᾬ",
   "*)/|a": "ᾌ",
+  "*)/a|": "ᾌ",
   "*)/|h": "ᾜ",
+  "*)/h|": "ᾜ",
   "*)/|w": "ᾬ",
+  "*)/w|": "ᾬ",
   "*)=A": "Ἆ",
   "*)=H": "Ἦ",
   "*)=I": "Ἶ",
@@ -107,11 +137,17 @@
   "*)=i": "Ἶ",
   "*)=w": "Ὦ",
   "*)=|A": "ᾎ",
+  "*)=A|": "ᾎ",
   "*)=|H": "ᾞ",
+  "*)=H|": "ᾞ",
   "*)=|W": "ᾮ",
+  "*)=W|": "ᾮ",
   "*)=|a": "ᾎ",
+  "*)=a|": "ᾎ",
   "*)=|h": "ᾞ",
+  "*)=h|": "ᾞ",
   "*)=|w": "ᾮ",
+  "*)=w|": "ᾮ",
   "*)A": "Ἀ",
   "*)E": "Ἐ",
   "*)H": "Ἠ",
@@ -131,11 +167,17 @@
   "*)\\o": "Ὂ",
   "*)\\w": "Ὢ",
   "*)\\|A": "ᾊ",
+  "*)\\A|": "ᾊ",
   "*)\\|H": "ᾚ",
+  "*)\\H|": "ᾚ",
   "*)\\|W": "ᾪ",
+  "*)\\W|": "ᾪ",
   "*)\\|a": "ᾊ",
+  "*)\\a|": "ᾊ",
   "*)\\|h": "ᾚ",
+  "*)\\h|": "ᾚ",
   "*)\\|w": "ᾪ",
+  "*)\\w|": "ᾪ",
   "*)a": "Ἀ",
   "*)e": "Ἐ",
   "*)h": "Ἠ",
@@ -143,11 +185,17 @@
   "*)o": "Ὀ",
   "*)w": "Ὠ",
   "*)|A": "ᾈ",
+  "*)A|": "ᾈ",
   "*)|H": "ᾘ",
+  "*)H|": "ᾘ",
   "*)|W": "ᾨ",
+  "*)W|": "ᾨ",
   "*)|a": "ᾈ",
+  "*)a|": "ᾈ",
   "*)|h": "ᾘ",
+  "*)h|": "ᾘ",
   "*)|w": "ᾨ",
+  "*)w|": "ᾨ",
   "*+I": "Ϊ",
   "*+U": "Ϋ",
   "*+i": "Ϊ",

From f8de775fced25765a8e9d29457789b544d35e947 Mon Sep 17 00:00:00 2001
From: zfletch <zfletch2@gmail.com>
Date: Fri, 30 Apr 2021 10:49:19 -0400
Subject: [PATCH 2/3] use standard diacritic order for uppercase letters

In `unicode_to_beta_code.json`, use the diacritic order specified by the
[TLG Beta Code Manual web
page](http://stephanus.tlg.uci.edu/encoding.php).
---
 unicode_to_beta_code.json | 54 +++++++++++++++++++--------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/unicode_to_beta_code.json b/unicode_to_beta_code.json
index 07b9a2d..10ec9fb 100644
--- a/unicode_to_beta_code.json
+++ b/unicode_to_beta_code.json
@@ -197,14 +197,14 @@
   "ᾅ": "a(/|",
   "ᾆ": "a)=|",
   "ᾇ": "a(=|",
-  "ᾈ": "*)|a",
-  "ᾉ": "*(|a",
-  "ᾊ": "*)\\|a",
-  "ᾋ": "*(\\|a",
-  "ᾌ": "*)/|a",
-  "ᾍ": "*(/|a",
-  "ᾎ": "*)=|a",
-  "ᾏ": "*(=|a",
+  "ᾈ": "*)a|",
+  "ᾉ": "*(a|",
+  "ᾊ": "*)\\a|",
+  "ᾋ": "*(\\a|",
+  "ᾌ": "*)/a|",
+  "ᾍ": "*(/a|",
+  "ᾎ": "*)=a|",
+  "ᾏ": "*(=a|",
   "ᾐ": "h)|",
   "ᾑ": "h(|",
   "ᾒ": "h)\\|",
@@ -213,14 +213,14 @@
   "ᾕ": "h(/|",
   "ᾖ": "h)=|",
   "ᾗ": "h(=|",
-  "ᾘ": "*)|h",
-  "ᾙ": "*(|h",
-  "ᾚ": "*)\\|h",
-  "ᾛ": "*(\\|h",
-  "ᾜ": "*)/|h",
-  "ᾝ": "*(/|h",
-  "ᾞ": "*)=|h",
-  "ᾟ": "*(=|h",
+  "ᾘ": "*)h|",
+  "ᾙ": "*(h|",
+  "ᾚ": "*)\\h|",
+  "ᾛ": "*(\\h|",
+  "ᾜ": "*)/h|",
+  "ᾝ": "*(/h|",
+  "ᾞ": "*)=h|",
+  "ᾟ": "*(=h|",
   "ᾠ": "w)|",
   "ᾡ": "w(|",
   "ᾢ": "w)\\|",
@@ -229,21 +229,21 @@
   "ᾥ": "w(/|",
   "ᾦ": "w)=|",
   "ᾧ": "w(=|",
-  "ᾨ": "*)|w",
-  "ᾩ": "*(|w",
-  "ᾪ": "*)\\|w",
-  "ᾫ": "*(\\|w",
-  "ᾬ": "*)/|w",
-  "ᾭ": "*(/|w",
-  "ᾮ": "*)=|w",
-  "ᾯ": "*(=|w",
+  "ᾨ": "*)w|",
+  "ᾩ": "*(w|",
+  "ᾪ": "*)\\w|",
+  "ᾫ": "*(\\w|",
+  "ᾬ": "*)/w|",
+  "ᾭ": "*(/w|",
+  "ᾮ": "*)=w|",
+  "ᾯ": "*(=w|",
   "ᾲ": "a\\|",
   "ᾳ": "a|",
   "ᾴ": "a/|",
   "ᾶ": "a=",
   "ᾷ": "a=|",
   "Ὰ": "*\\a",
-  "ᾼ": "*|a",
+  "ᾼ": "*a|",
   "᾽": "'",
   "ῂ": "h\\|",
   "ῃ": "h|",
@@ -252,7 +252,7 @@
   "ῇ": "h=|",
   "Ὲ": "*\\e",
   "Ὴ": "*\\h",
-  "ῌ": "*|h",
+  "ῌ": "*h|",
   "ῒ": "i\\+",
   "ῖ": "i=",
   "ῗ": "i=+",
@@ -271,6 +271,6 @@
   "ῷ": "w=|",
   "Ὸ": "*\\o",
   "Ὼ": "*\\w",
-  "ῼ": "*|w",
+  "ῼ": "*w|",
   "—": "_"
 }

From e3f2b0412fbed6d8ea3ddefba353c6d9842b5239 Mon Sep 17 00:00:00 2001
From: zfletch <zfletch2@gmail.com>
Date: Fri, 30 Apr 2021 11:10:13 -0400
Subject: [PATCH 3/3] include tlg spec and exceptions in readme

---
 README.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/README.md b/README.md
index d54b7d7..ece8718 100644
--- a/README.md
+++ b/README.md
@@ -2,6 +2,19 @@
 
 Map of Greek Beta Code characters to Unicode and from Unicode to Beta Code.
 
+## Standard
+
+The mappings in this repository aim mostly to conform to the TLG standard
+specified [here](http://stephanus.tlg.uci.edu/encoding.php).
+
+Not every application that uses Greek Beta Code follows the TLG standard exactly.
+The mappings try to capture these nonstandard uses without breaking Beta Code encoded
+according to the standard in the following ways:
+
+* Lowercase Latin letters can be used in the Beta Code (e.g. `a`, `w=`)
+* Uppercase Greek letters can be keyed 1. asterisk, 2. breathing, 3. accent, 4. iota subscript, 5. letter (e.g. `*(=|W`)
+* Uppercase Greek letters can be keyed 1. asterisk, 2. letter, 3. breathing, 4. accent, 5. iota subscript (e.g. `*W(=|`)
+
 ## Example uses
 
 * [https://github.com/perseids-tools/beta-code-js](https://github.com/perseids-tools/beta-code-js)