More symbols

2 files changed, 101 insertions, 120 deletions

diff --git a/TODOsymbols b/TODOsymbols
index 3d3d63e..2675e47 100644
--- a/TODOsymbols
+++ b/TODOsymbols
@@ -1,113 +1,18 @@
-aacuced
-aacusc
-aangsc
-acircsc # acirc is 00e5...
-agravesc
 atildepr
-atildesc
-aumlsc
 bantuo
 Bantuo
 ccedpr
-ccedsc
-clenis
-click
-ctlig
 dlessj1
 dlessj2
-eacusc
-ecircsc
 edhpr
-egravesc
-elenis
-Elenis
-elenisacu
-Elenisacu
-Elenisfrown
-elenisgrave
-eth
-eumlsc
 ff0
 ff2
 ff3
 hg
-iacusc
-icircsc
-igravesc
 itildepr
-iumlsc
-ntildesc
-oacusc
-obr
-ocircsc
-ogravesc
 ohgcirc
-otildesc
-oumlsc
 par
 reva
-revsc
 roasper
 ruasper
-uacusc
-ucircsc
-uumlsc
-vavpath
-vavsheva
-vdftheta
-vuml
-vvf
-wacu
-wapos
-wasper
-Wasper
-wasperacu
-wasperfrown
-Wasperfrown
-wcirc
-wdotbl
-wgrave
-whacek
-wisub
-wisubacu
-wisubfrown
-wlenis
-Wlenis
-wlenisacu
-Wlenisacu
-wlenisfrown
-wlenisisub
-wmac
 woqab
-wyn
-Wyn
-xdotab
-xi
-Xi
-yacu
-yacusc
-ybreve
-ycirc
-ydotab
-Ydotab
-ygh
-Ygh
-ygra
-ymac
-ymacacu
-ymacbreve
-ytilde
-yuml
-Yundl
-zacu
-zbreve
-zced
-zdotab
-zdotbl
-zeta
-Zeta
-zh
-zhacek
-Zhacek
-zhacekdotab
-zmac
diff --git a/symbols b/symbols
index 6dcb241..ffccee4 100644
--- a/symbols
+++ b/symbols
@@ -1,29 +1,10 @@
 # All symbols can be represented either as &symbol; or _symbol_ so
 # parse these with symbolstosed to create sed rules.
 
-# A large list of these in Help/Advanced/symbols.htm
-
-# punctuation
-revsc ·
-
-# Phonetic symbols
-ccedpr θ
-edhpr ð
-zh ʝ
-
-# These are extras which aren't documented in the symbol list
-
-oq ‘
-cq ’
-
-# Basic HTML entities
-# TODO: generate these from http://www.w3.org/TR/html4/sgml/entities.html or http://www.w3.org/TR/xml-entity-names/
-\#038 \&
-oacu ó
-ocirc ô
+# Many of these are documented in the Help/Advanced/ directory of the OED CDROM
 
 # notes:
-# 'frown' is sad face circumflex ('inverted breve', in case of greek just use circumflex)
+# 'frown' is sad face circumflex ('inverted breve', in case of greek just use tilde)
 # 'tilde' is wiggly circumflex
 # 'circ' is circumflex (^)
 # 'dotab' is dot above
@@ -35,18 +16,20 @@ ocirc ô
 # 'ced' is cedilla e.g. garcon
 # 'breve' U+0306
 # 'ac' acute U+0301
+# 'sc' small capitals (changed to normal capitals here)
 
 # unknown:
 # pr
-# sc
-# ced
 
 # going through in alphabetical order
 \#038 \&
 \#062 >
 aacu á
+aacuced á̧
+aacusc Á
 Aacu Á
 aang å
+aangsc Å
 Aang Å
 aasper ἁ
 Aasper Ἁ
@@ -60,6 +43,7 @@ abreve ă
 Abreve Ă
 aced a̧
 acirc â
+acircsc Â
 Acirc Â
 adotab ȧ
 ae æ
@@ -77,6 +61,7 @@ aepr ɶ
 afrown â
 Afrown Â
 agrave à
+agravesc À
 Agrave À
 ahacek ǎ
 ahook ả
@@ -107,7 +92,9 @@ amacundl ā̲
 asg ᵹ
 Asg Ᵹ
 atilde ã
+atildesc Ã
 auml ä
+aumlsc Ä
 Auml Ä
 aundl a̲
 ayin ʿ
@@ -124,6 +111,7 @@ cbr }
 cbreve c̆
 Cbreve C̆
 cced ç
+ccedsc Ç
 Cced Ç
 ccirc ĉ
 cdsb ⟧
@@ -135,8 +123,12 @@ chacekdotab č̇
 chi χ
 Chi Χ
 chook ƈ
+clenis c̓
+click ǀ
 cmac c̄
+cq ’
 ctilde c̃
+ctlig ct
 cyra а
 cyrd д
 cyre э
@@ -170,6 +162,7 @@ dlessj3 ȷ
 dtilde d̃
 dundl ḏ
 eacu é
+eacusc É
 Eacu É
 eacudotbl ẹ́
 easper ἑ
@@ -179,8 +172,10 @@ Easperacu Ἕ
 easpergrave ἓ
 ebreve ĕ
 ecirc ê
+ecircsc Ê
 Ecirc Ê
 egrave è
+egravesc È
 edh ð
 Edh Ð
 edotab ė
@@ -199,6 +194,12 @@ Ehook Ẻ
 ehookacu ẻ́
 ehookmac ẻ̄
 ehookmacbreve ẻ̄̆
+elenis ἐ
+Elenis Ἐ
+elenisacu ἔ
+Elenisacu Ἔ
+Elenisfrown Ἐ̃
+elenisgrave ἒ
 emac ē
 Emac Ē
 emacacu ḗ
@@ -211,9 +212,11 @@ eszett ß
 eta η
 Eta Η
 etaisub ῃ
+eth ð
 etilde ẽ
-euml ë
+euml ë
 eumlacu ë́
+eumlsc Ë
 eundl e̱
 eundlacu é̱
 fata ɑ
@@ -300,6 +303,7 @@ hlenisfrown ἦ
 hlenisgrave ἢ
 hundl ẖ
 iacu í
+iacusc Í
 Iacu Í
 iasper ἱ
 Iasper Ἱ
@@ -312,11 +316,13 @@ Ibreve Ĭ
 ibrevemac ĭ̄
 iced i̧
 icirc î
+icircsc Î
 Icirc Î
 ifflig ff
 ifilig fi
 ifrbl ḭ
 igrave ì
+igravesc Ì
 ihacek ǐ
 ilenis ἰ
 Ilenis Ἰ
@@ -337,6 +343,7 @@ Iota Ι
 istlig st
 itilde ĩ
 iuml ï
+iumlsc Ï
 iundl i̲
 jbreve j̆
 jhacek ǰ
@@ -390,10 +397,12 @@ ng ɳ
 nhacek ň
 nmac n̄
 ntilde ñ
+ntildesc Ñ
 nu ν
 Nu Ν
 nundl ṉ
 oacu ó
+oacusc Ó
 Oacu Ó
 oasper ὁ
 Oasper Ὁ
@@ -408,10 +417,12 @@ obarpr ø
 obigb ⎨
 obigpren ⎜
 obigsb ⎥
+obr {
 obreve ŏ
 Obreve Ŏ
 obrevemac ŏ̄
 ocirc ô
+ocircsc Ô
 Ocirc Ô
 ocircgra ồ
 odotab ȯ
@@ -426,6 +437,7 @@ oepr œ
 oetilde œ̃
 ofrown ȏ
 ograve ò
+ogravesc Ò
 ohacek ǒ
 ohook ỏ
 ohookacu ỏ́
@@ -450,9 +462,12 @@ Omicron Ο
 ope ɛ
 opemac ɛ̄
 opetilde ɛ̃
+oq ‘
 otilde õ
 otildepr õ
+otildesc Õ
 ouml ö
+oumlsc Ö
 Ouml Ö
 oumlmac ȫ
 oundl o̲
@@ -496,6 +511,7 @@ revope ɜ
 revopehook ɝ
 revr ɹ
 revrmac ɹ̄
+revsc ?
 revv ʌ
 revvmac ʌ̄
 revvtilde ʌ̃
@@ -575,6 +591,7 @@ ttilde t̃
 tundl ṯ
 Tundl T̲
 uacu ú
+uacusc Ú
 Uacu Ú
 uang ů
 uangtilde ů̃
@@ -586,6 +603,7 @@ Uasperfrown Ὗ
 ubar ʉ
 ubreve ŭ
 ucirc û
+ucircsc Û
 Ucirc Û
 uda ɐ
 udA ɐ
@@ -613,10 +631,68 @@ Upsilon Υ
 utilde ũ
 utildeacu ṹ
 uuml ü
+uumlsc Ü
 Uuml Ü
 uumlacu ǘ
 uumlcirc ü̂
 uumlgra ǜ
 uumlhacek ǚ
 uumlmac ǖ
-
+vavpath וַ
+vavsheva וְ
+vdftheta ɵ
+vuml v̈
+vvf ɣ
+wacu ẃ
+wapos w̓
+wasper ὡ
+Wasper Ὡ
+wasperacu ὥ
+wasperfrown ὧ
+Wasperfrown Ὧ
+wcirc ẘ
+wdotbl ẉ
+wgrave ẁ
+whacek w̌
+wisub ῳ
+wisubacu ῴ
+wisubfrown ῷ
+wlenis ὠ
+Wlenis Ὠ
+wlenisacu ὤ
+Wlenisacu Ὤ
+wlenisfrown ὦ
+wlenisisub ᾠ
+wmac w̄
+wyn ƿ
+Wyn Ƿ
+xdotab ẋ
+xi χ
+Xi Χ
+yacu ý
+yacusc Ý
+ybreve y̆
+ycirc ŷ
+ydotab ẏ
+Ydotab Ẏ
+ygh ȝ
+Ygh Ȝ
+ygra ỳ
+ymac ȳ
+ymacacu ȳ́
+ymacbreve ȳ̆
+ytilde ỹ
+yuml ÿ
+Yundl Y̲
+zacu ź
+zbreve z̆
+zced z̧
+zdotab ż
+zdotbl ẓ
+zeta ζ
+Zeta Ζ
+zh ʓ
+zhacek ž
+Zhacek Ž
+zhacekdotab ž̇
+zmac z̄