From d4ade2bc1c44d9890209716557a88774851fbe3b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?G=C3=BCnter=20Milde?= Date: Mon, 1 Apr 2019 19:10:06 +0200 Subject: [PATCH] unicodesymbols: add Hebrew nikud symbols and presentation forms. The "nikud" (vowel) signs, shindot, and shindot are combining Unicode characters. However, LaTeX-Hebrew expects them as postfix characters, not accent macros (cf. www.cs.tau.ac.il/~stoledo/Bib/Pubs/vowels.pdf). --- .../152-modifiers-presentation_he.lyx | 183 ++++++++++++++++++ development/autotests/unreliableTests | 2 +- lib/unicodesymbols | 91 ++++++--- 3 files changed, 248 insertions(+), 28 deletions(-) create mode 100644 autotests/export/latex/unicodesymbols/152-modifiers-presentation_he.lyx diff --git a/autotests/export/latex/unicodesymbols/152-modifiers-presentation_he.lyx b/autotests/export/latex/unicodesymbols/152-modifiers-presentation_he.lyx new file mode 100644 index 0000000000..3d8ec50948 --- /dev/null +++ b/autotests/export/latex/unicodesymbols/152-modifiers-presentation_he.lyx @@ -0,0 +1,183 @@ +#LyX 2.4 created this file. For more info see https://www.lyx.org/ +\lyxformat 569 +\begin_document +\begin_header +\save_transient_properties true +\origin unavailable +\textclass article +\use_default_options true +\maintain_unincluded_children false +\language english +\language_package default +\inputencoding utf8 +\fontencoding auto +\font_roman "lmodern" "default" +\font_sans "lmss" "default" +\font_typewriter "lmtt" "default" +\font_math "auto" "auto" +\font_default_family default +\use_non_tex_fonts false +\font_sc false +\font_osf false +\font_sf_scale 100 100 +\font_tt_scale 100 100 +\use_microtype false +\use_dash_ligatures true +\graphics default +\default_output_format pdf2 +\output_sync 0 +\bibtex_command default +\index_command default +\paperfontsize default +\spacing single +\use_hyperref false +\papersize default +\use_geometry false +\use_package amsmath 1 +\use_package amssymb 1 +\use_package cancel 1 +\use_package esint 1 +\use_package mathdots 1 +\use_package mathtools 1 +\use_package mhchem 1 +\use_package stackrel 1 +\use_package stmaryrd 1 +\use_package undertilde 1 +\cite_engine basic +\cite_engine_type default +\biblio_style plain +\use_bibtopic false +\use_indices false +\paperorientation portrait +\suppress_date false +\justification false +\use_refstyle 1 +\use_minted 0 +\branch na +\selected 0 +\filename_suffix 0 +\color #faf0e6 +\end_branch +\index Index +\shortcut idx +\color #008000 +\end_index +\secnumdepth 3 +\tocdepth 3 +\paragraph_separation indent +\paragraph_indentation default +\is_math_indent 0 +\math_numbering_side default +\quotes_style english +\dynamic_quotes 0 +\papercolumns 1 +\papersides 1 +\paperpagestyle default +\tablestyle default +\tracking_changes false +\output_changes false +\html_math_output 0 +\html_css_as_file 0 +\html_be_strict false +\end_header + +\begin_body + +\begin_layout Subsection* +152 Alphabetic Presentation Forms +\end_layout + +\begin_layout Labeling +\labelwidthstring 00.00.0000 +FB00 ff fi fl ffi ffl +\begin_inset Branch na +inverted 0 +status open + +\begin_layout Standard +ſt st +\end_layout + +\end_inset + + +\end_layout + +\begin_layout Labeling +\labelwidthstring 00.00.0000 +FB10 +\begin_inset Branch na +inverted 0 +status open + +\begin_layout Standard +ﬓ ﬔ ﬕ ﬖ ﬗ +\end_layout + +\end_inset + + +\lang hebrew +יִ +\begin_inset Branch na +inverted 0 +status open + +\begin_layout Standard +ﬞ +\end_layout + +\end_inset + +ײַ +\end_layout + +\begin_layout Labeling +\labelwidthstring 00.00.0000 +FB20 +\lang hebrew + +\begin_inset Branch na +inverted 0 +status open + +\begin_layout Standard + +\lang hebrew +ﬠ ﬡ ﬢ ﬣ ﬤ ﬥ ﬦ ﬧ ﬨ ﬩ +\end_layout + +\end_inset + + שׁ שׂ שּׁ שּׂ אַ אָ +\end_layout + +\begin_layout Labeling +\labelwidthstring 00.00.0000 +FB30 +\lang hebrew +אּ בּ גּ דּ הּ וּ זּ טּ יּ ךּ כּ לּ מּ +\end_layout + +\begin_layout Labeling +\labelwidthstring 00.00.0000 +FB40 +\lang hebrew +נּ סּ ףּ פּ צּ קּ רּ שּ תּ וֹ בֿ כֿ פֿ +\begin_inset Branch na +inverted 0 +status open + +\begin_layout Standard + +\lang hebrew +ﭏ +\end_layout + +\end_inset + + +\end_layout + +\end_body +\end_document diff --git a/development/autotests/unreliableTests b/development/autotests/unreliableTests index 2e57b6480e..d3ce96c9ff 100644 --- a/development/autotests/unreliableTests +++ b/development/autotests/unreliableTests @@ -80,7 +80,7 @@ templates/examples/Books/Springer_Contributed_Books.* # TeXLive does not set up Hebrew 8-bit TeX fonts # We use the external package culmus-latex # https://sourceforge.net/projects/ivritex/files/culmus-latex/culmus-latex-0.7/ -export/export/latex/unicodesymbols/012-31-hebrew_he-thai_pdf2 +export/export/latex/unicodesymbols/.*_he.*pdf2 export/.*/he/.*((dvi|pdf.?)|_texF) diff --git a/lib/unicodesymbols b/lib/unicodesymbols index 1120c1a71f..c4f40a6b39 100644 --- a/lib/unicodesymbols +++ b/lib/unicodesymbols @@ -990,7 +990,7 @@ 0x045d "\\`\\cyri" "textcyrillic" "" # CYRILLIC SMALL LETTER I WITH GRAVE 0x045e "\\cyrushrt" "textcyrillic" "force=euc-jp" # CYRILLIC SMALL LETTER SHORT U 0x045f "\\cyrdzhe" "textcyrillic" "force=euc-jp" # CYRILLIC SMALL LETTER DZHE -#0x460-0x48f archaic cyrillic characters missing in font encoding T2A, FIXME how about X2? +#0x460 ... 0x48f archaic cyrillic characters missing in font encoding T2A, FIXME how about X2? 0x0490 "\\CYRGUP" "textcyrillic" "" # CYRILLIC CAPITAL LETTER GHE WITH UPTURN 0x0491 "\\cyrgup" "textcyrillic" "" # CYRILLIC SMALL LETTER GHE WITH UPTURN 0x0492 "\\CYRGHCRS" "textcyrillic" "" # CYRILLIC CAPITAL LETTER GHE WITH STROKE @@ -1100,34 +1100,34 @@ # # 12 Hebrew # -#0x0591 "" "" "combining,force" "" "" # HEBREW ACCENT ETNAHTA -# Fixme: Placement of the "nikud" (vowel) signs is bad. -# Maybe try ideas from https://www.culturestrings.org/typography/culmusx/ ? -0x05b0 "\\sheva" "" "combining,force" "" "" # HEBREW POINT SHEVA -0x05b1 "\\hatafsegol" "" "combining,force" "" "" # HEBREW POINT HATAF SEGOL -0x05b2 "\\hatafpatah" "" "combining,force" "" "" # HEBREW POINT HATAF PATAH -0x05b3 "\\hatafqamats" "" "combining,force" "" "" # HEBREW POINT HATAF QAMATS -0x05b4 "\\hiriq" "" "combining,force" "" "" # HEBREW POINT HIRIQ -0x05b5 "\\tsere" "" "combining,force" "" "" # HEBREW POINT TSERE -0x05b6 "\\segol" "" "combining,force" "" "" # HEBREW POINT SEGOL -0x05b7 "\\patah" "" "combining,force" "" "" # HEBREW POINT PATAH -0x05b8 "\\qamats" "" "combining,force" "" "" # HEBREW POINT QAMATS -0x05b9 "\\holam" "" "combining,force" "" "" # HEBREW POINT HOLAM -#0x05ba "" "" "combining,force" "" "" # HEBREW POINT HOLAM HASER FOR VAV -0x05bb "\\qubuts" "" "combining,force" "" "" # HEBREW POINT QUBUTS -0x05bc "\\dagesh" "" "combining,force" "" "" # HEBREW POINT DAGESH OR MAPIQ -0x05bd "\\meteg" "" "combining,force" "" "" # HEBREW POINT METEG -0x05be "\\maqaf" "" "force=cp1255;utf8;utf8-cjk" "" "" # HEBREW PUNCTUATION MAQAF -#0x05bf "" "" "combining,force" "" "" # HEBREW POINT RAFE -#0x05c0 "" "" "" "" "" # HEBREW PUNCTUATION PASEQ -# shindot and shindot are actually combining unicode characters but work fine as postfix +# The "nikud" (vowel) signs, shindot, and shindot are combining Unicode +# characters. However, LaTeX-Hebrew expects them as postfix characters, not +# accent macros (cf. www.cs.tau.ac.il/~stoledo/Bib/Pubs/vowels.pdf). +#0x0591 "" "" "" "" "" # HEBREW ACCENT ETNAHTA +0x05b0 "\\sheva" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT SHEVA +0x05b1 "\\hatafsegol" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT HATAF SEGOL +0x05b2 "\\hatafpatah" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT HATAF PATAH +0x05b3 "\\hatafqamats" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT HATAF QAMATS +0x05b4 "\\hiriq" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT HIRIQ +0x05b5 "\\tsere" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT TSERE +0x05b6 "\\segol" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT SEGOL +0x05b7 "\\patah" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT PATAH +0x05b8 "\\qamats" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT QAMATS +0x05b9 "\\holam" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT HOLAM +#0x05ba "" "" "" "" "" # HEBREW POINT HOLAM HASER FOR VAV +0x05bb "\\qubuts" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT QUBUTS +0x05bc "\\dagesh" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT DAGESH OR MAPIQ +0x05bd "\\meteg" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT METEG +0x05be "\\maqaf" "" "force=cp1255;utf8;utf8-cjk" "" "" # HEBREW PUNCTUATION MAQAF +0x05bf "\\rafe" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT RAFE +0x05c0 "\\paseq" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW PUNCTUATION PASEQ 0x05c1 "\\shindot" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT SHIN DOT 0x05c2 "\\sindot" "" "force=cp1255;utf8;utf8-cjk;utf8x" "" "" # HEBREW POINT SIN DOT -0x05c3 "\\sofpasuq" "" "force=cp1255;utf8;utf8-cjk" "" "" # HEBREW PUNCTUATION SOF PASUQ -#0x05c4 "" "" "combining,force" "" "" # HEBREW MARK UPPER DOT -#0x05c5 "" "" "combining,force" "" "" # HEBREW MARK LOWER DOT -#0x05c6 "" "" "" "" "" # HEBREW PUNCTUATION NUN HAFUKHA -#0x05c7 "" "" "combining,force" "" "" # HEBREW POINT QAMATS QATAN +0x05c3 "\\sofpasuq" "" "force=cp1255;utf8;utf8-cjk" "" "" # HEBREW PUNCTUATION SOF PASUQ +#0x05c4 "" "" "" "" "" # HEBREW MARK UPPER DOT +#0x05c5 "" "" "" "" "" # HEBREW MARK LOWER DOT +#0x05c6 "" "" "" "" "" # HEBREW PUNCTUATION NUN HAFUKHA +#0x05c7 "" "" "" "" "" # HEBREW POINT QAMATS QATAN 0x05d0 "\\hebalef" "" "force=utf8;utf8-cjk" "\\aleph" "amssymb" # HEBREW LETTER ALEF 0x05d1 "\\hebbet" "" "force=utf8;utf8-cjk" "\\beth" "amssymb" # HEBREW LETTER BET 0x05d2 "\\hebgimel" "" "force=utf8;utf8-cjk" "\\gimel" "amssymb" # HEBREW LETTER GIMEL @@ -3719,6 +3719,43 @@ 0xfb03 "ffi" "" "force,notermination=text" "" "" # LATIN SMALL LIGATURE FFI 0xfb04 "ffl" "" "force,notermination=text" "" "" # LATIN SMALL LIGATURE FFL # +0xfb1d "\\hebyod\\hiriq" "" "" "" "" # HEBREW LETTER YOD WITH HIRIQ +#0xfb1e "" "" "" "" "" # HEBREW POINT JUDEO-SPANISH VARIKA +0xfb1f "\\doubleyod\\patah" "" "" "" "" # HEBREW LIGATURE YIDDISH YOD YOD PATAH +0xfb2a "\\hebshin\\shindot" "" "" "" "" # HEBREW LETTER SHIN WITH SHIN DOT +0xfb2b "\\hebshin\\sindot" "" "" "" "" # HEBREW LETTER SHIN WITH SIN DOT +0xfb2c "\\hebshin\\shindot\\dagesh" "" "" "" "" # HEBREW LETTER SHIN WITH DAGESH AND SHIN DOT +0xfb2d "\\hebshin\\sindot\\dagesh" "" "" "" "" # HEBREW LETTER SHIN WITH DAGESH AND SIN DOT +0xfb2e "\\hebalef\\patah" "" "" "" "" # HEBREW LETTER ALEF WITH PATAH +0xfb2f "\\hebalef\\qamats" "" "" "" "" # HEBREW LETTER ALEF WITH QAMATS +0xfb30 "\\hebalef\\dagesh" "" "" "" "" # HEBREW LETTER ALEF WITH MAPIQ +0xfb31 "\\hebbet\\dagesh" "" "" "" "" # HEBREW LETTER BET WITH DAGESH +0xfb32 "\\hebgimel\\dagesh" "" "" "" "" # HEBREW LETTER GIMEL WITH DAGESH +0xfb33 "\\hebdalet\\dagesh" "" "" "" "" # HEBREW LETTER DALET WITH DAGESH +0xfb34 "\\hebhe\\dagesh" "" "" "" "" # HEBREW LETTER HE WITH MAPIQ +0xfb35 "\\hebvav\\dagesh" "" "" "" "" # HEBREW LETTER VAV WITH DAGESH +0xfb36 "\\hebzayin\\dagesh" "" "" "" "" # HEBREW LETTER ZAYIN WITH DAGESH +0xfb38 "\\hebtet\\dagesh" "" "" "" "" # HEBREW LETTER TET WITH DAGESH +0xfb39 "\\hebyod\\dagesh" "" "" "" "" # HEBREW LETTER YOD WITH DAGESH +0xfb3a "\\hebfinalkaf\\dagesh" "" "" "" "" # HEBREW LETTER FINAL KAF WITH DAGESH +0xfb3b "\\hebkaf\\dagesh" "" "" "" "" # HEBREW LETTER KAF WITH DAGESH +0xfb3c "\\heblamed\\dagesh" "" "" "" "" # HEBREW LETTER LAMED WITH DAGESH +0xfb3e "\\hebmem\\dagesh" "" "" "" "" # HEBREW LETTER MEM WITH DAGESH +0xfb40 "\\hebnun\\dagesh" "" "" "" "" # HEBREW LETTER NUN WITH DAGESH +0xfb41 "\\hebsamekh\\dagesh" "" "" "" "" # HEBREW LETTER SAMEKH WITH DAGESH +0xfb43 "\\hebfinalpe\\dagesh" "" "" "" "" # HEBREW LETTER FINAL PE WITH DAGESH +0xfb44 "\\hebpe\\dagesh" "" "" "" "" # HEBREW LETTER PE WITH DAGESH +0xfb46 "\\hebtsadi\\dagesh" "" "" "" "" # HEBREW LETTER TSADI WITH DAGESH +0xfb47 "\\hebqof\\dagesh" "" "" "" "" # HEBREW LETTER QOF WITH DAGESH +0xfb48 "\\hebresh\\dagesh" "" "" "" "" # HEBREW LETTER RESH WITH DAGESH +0xfb49 "\\hebshin\\dagesh" "" "" "" "" # HEBREW LETTER SHIN WITH DAGESH +0xfb4a "\\hebtav\\dagesh" "" "" "" "" # HEBREW LETTER TAV WITH DAGESH +0xfb4b "\\hebvav\\holam" "" "" "" "" # HEBREW LETTER VAV WITH HOLAM +0xfb4c "\\hebbet\\rafe" "" "" "" "" # HEBREW LETTER BET WITH RAFE +0xfb4d "\\hebkaf\\rafe" "" "" "" "" # HEBREW LETTER KAF WITH RAFE +0xfb4e "\\hebpe\\rafe" "" "" "" "" # HEBREW LETTER PE WITH RAFE +#0xfb4f "" "" "" "" "" # HEBREW LIGATURE ALEF LAMED +# # 246 Mathematical Alphanumeric Symbols # 0x1d400 "" "" "force=utf8;utf8-cjk" "\\mathbf{A}" "" # 𝐀 MATHEMATICAL BOLD CAPITAL A