summaryrefslogtreecommitdiff
path: root/macros/latex/contrib/semantex/stripsemantex.lua
blob: 1ebce1f716fcb37724021cc266f4f204578cd815 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
-- aliases for protected environments
local assert, io_open
    = assert, io.open

-- load the ltn12 module
local ltn12 = require("ltn12")

-- No more global accesses after this point
if _VERSION == "Lua 5.2" then _ENV = nil end

-- copy a file
copy_file = function(path_src, path_dst)
  ltn12.pump.all(
      ltn12.source.file(assert(io_open(path_src, "rb"))),
      ltn12.sink.file(assert(io_open(path_dst, "wb")))
    )
end

openFile = function(file)
 f = io.open(file, "r")
 filecontent = f:read("*all")
 local beginDocPosition = filecontent:find('\\begin{document}')
 if not beginDocPosition then
	tex.sprint( [[\begingroup\ExplSyntaxOn
		\msg_fatal:nnn { stripsemantex } { begin_document_not_found } { ]] .. file .. [[ }
		\endgroup]] )
	return
 end
 precontent = filecontent:sub(1,beginDocPosition-1)
 content = filecontent:sub(beginDocPosition,-1)
 f:close()
end

closeFile = function(file)
 f = io.open(file, "w")
 f:write(precontent .. content)
 f:close()
end

removeStricttexFormatting = function(str)
	-- We do this in case the package "stricttex" was used
	str = str:gsub('numberZERO','0')
	str = str:gsub('numberONE','1')
	str = str:gsub('numberTWO','2')
	str = str:gsub('numberTHREE','3')
	str = str:gsub('numberFOUR','4')
	str = str:gsub('numberFIVE','5')
	str = str:gsub('numberSIX','6')
	str = str:gsub('numberSEVEN','7')
	str = str:gsub('numberEIGHT','8')
	str = str:gsub('numberNINE','9')
	str = str:gsub('symbolPRIME','\'')
	return str
end

addIDsToRegisters = function(str)
	str = removeStricttexFormatting(str)
	content = content:gsub('\\' .. str .. '([^%a])' ,'\\SemantexIDcommand{}\\' .. str .. '%1')
	-- '%f[^%a]' does not work here, as it will not react if the last character of str is a number,
	-- which stricttex allows.
	-- Because of this choice, there will be an issue if you use stricttex and let
	-- \<command> by a SemanTeX command and \<command>' be a non-SemanTeX command.
	-- So simply *don't do that*.
end

removeSuperfluousIDs = function()
	content = content:gsub('parent(%s*)=(%s*)\\SemantexIDcommand{}','parent%1=%2')
	content = content:gsub('class(%s*)=(%s*)\\SemantexIDcommand{}','class%1=%2')
	content = content:gsub('clone(%s*)=(%s*)\\SemantexIDcommand{}','clone%1=%2')
	content = content:gsub('copy(%s*)=(%s*)\\SemantexIDcommand{}','copy%1=%2')
	content = content:gsub('\\New(%w+)Class(%s*{?)\\SemantexIDcommand{}','\\New%1Class%2')
	content = content:gsub('\\NewObject(%s*{?%s*)\\SemantexIDcommand{}(\\%w+%s*}?%s*{?%s*)\\SemantexIDcommand{}', '\\NewObject%1%2')
	content = content:gsub('\\SetupClass(%s*{?%s*)\\SemantexIDcommand{}', '\\SetupClass%1')
	content = content:gsub('\\SetupObject(%s*{?%s*)\\SemantexIDcommand{}', '\\SetupObject%1')
end

addNumbersToIDs = function()
	local n = 1	
	local p,q = string.find(content,'\\SemantexIDcommand{}')
	while q do
		content = content:sub(1,q-1) .. n .. content:sub(q,-1)
		p, q = string.find(content,'\\SemantexIDcommand{}')	
		n = n + 1
	end
end

semantexIDluacommand = function(id, source, output)
	local p, q = string.find(content, '\\SemantexIDcommand{' .. id .. '}')
	
	while p do
		content = content:sub(1,p-1) .. content:sub(q+1,-1)
		
		source = source:gsub('%s+', '')
		
		-- We do this in case the package "stricttex" was used
		source = removeStricttexFormatting(source)
		
		-- This is because #1's in the code becomes ##1
		-- in the .semtex file.
		source = source:gsub('#(%d)', '%1')
		
		local length = source:len()
	
		local i = 1
		
		local s
		
		while i <= length do
			s = content:sub(p,p)
			if s == source:sub(i,i) then
				content = content:sub(1 , p-1) .. content:sub(p+1, -1)
				i = i + 1
			elseif s:match('%s') then
				content = content:sub(1, p-1) .. content:sub(p+1, -1)
			elseif s == '%' then
				content = content:sub(1 , p-1) .. content:sub(p,-1):gsub('%%.-\n','',1)
			elseif s == '{' then
				-- In this case, we remove the corresponding right brace,
				-- once we find it
				local netto = 1 -- The current brace group level
				local q = 0 -- The position we have moved forward so far
				while netto > 0 do
					q = q + 1
					local e = content:sub(p+q,p+q)
					if e == '}' then
						netto = netto - 1
					elseif e == '{' then
						netto = netto + 1
					elseif e == '\\' then
						q = q + 1
					elseif e == '%' then
						content = content:sub(1, p+q-1) .. content:sub(p+q,-1):gsub('%%.-\n','',1)
						q = q - 1
					end
				end
				content = content:sub(1,p-1) .. content:sub(p+1,p+q-1) .. content:sub(p+q+1,-1)
			elseif s == '<' and content:sub(p+1,p+2) == '[>' then
				content = content:sub(1,p-1) .. content:sub(p+3,-1)
				i = i + 1
			elseif s == '<' and content:sub(p+1,p+2) == ']>' then
				content = content:sub(1,p-1) .. content:sub(p+3,-1)
				i = i + 1
			elseif source:sub(i,i) == '{' then
				-- In this case, we remove the corresponding right brace,
				-- once we find it
				local netto = 1 -- The current brace group level
				local q = 0 -- The position we have moved forward so far
				while netto > 0 do
					q = q + 1
					local e = source:sub(i+q,i+q)
					if e == '}' then
						netto = netto - 1
					elseif e == '{' then
						netto = netto + 1
					elseif e == '\\' then
						q = q + 1
					-- there is no chance that the source contains a %, so we do not
					-- check for this
					end
				end
				source = source:sub(1,i-1) .. source:sub(i+1,i+q-1) .. source:sub(i+q+1,-1)
				length = source:len()
			else
				tex.sprint( [[\begingroup\ExplSyntaxOn
				\msg_fatal:nnnn { stripsemantex } { source_not_expected } { ]] .. source:sub(i,i) .. [[ } { ]] .. s  .. [[ }
				\endgroup]] )
				break
			end
		end
		
		
		output = output:gsub('%s*\\sp {', '^{')
		output = output:gsub('%s*\\sb {', '_{')
		output = output:gsub('\\mathopen \\big ', '\\bigl')
		output = output:gsub('\\mathclose \\big ', '\\bigr')
		output = output:gsub('\\mathopen \\Big ', '\\Bigl')
		output = output:gsub('\\mathclose \\Big ', '\\Bigr')
		output = output:gsub('\\mathopen \\bigg ', '\\biggl')
		output = output:gsub('\\mathclose \\bigg ', '\\biggr')
		output = output:gsub('\\mathopen \\Bigg ', '\\Biggl')
		output = output:gsub('\\mathclose \\Bigg ', '\\Biggr')
		output = output:gsub('\\mathopen %(', '(')
		output = output:gsub('\\mathclose %)', ')')
		output = output:gsub('\\mathopen %[', '[')
		output = output:gsub('\\mathclose %]', ']')
		output = output:gsub('\\mathopen \\{', '\\{')
		output = output:gsub('\\mathclose \\}', '\\}')
		output = output:gsub('\\mathopen \\lbrace', '\\lbrace')
		output = output:gsub('\\mathclose \\rbrace', '\\rbrace')
		output = output:gsub('\\mathopen \\lbrack', '\\rbrack')
		output = output:gsub('\\mathclose \\rbrack', '\\rbrack')
		output = output:gsub('\\mathopen \\langle', '\\langle')
		output = output:gsub('\\mathclose \\rangle', '\\rangle')
		output = output:gsub('\\mathopen \\lvert', '\\rvert')
		output = output:gsub('\\mathclose \\rvert', '\\rvert')
		output = output:gsub('\\mathopen \\lVert', '\\rVert')
		output = output:gsub('\\mathclose \\rVert', '\\rVert')
		output = output:gsub('%^{\\prime }', '\'')
		output = output:gsub('%^{\\prime \\prime }', '\'\'')
		output = output:gsub('%^{\\prime \\prime \\prime }', '\'\'\'')
		output = output:gsub('%^{\\prime \\prime \\prime \\prime }', '\'\'\'\'')
		output = output:gsub('%^{\\prime \\prime \\prime \\prime \\prime }', '\'\'\'\'\'')
		
		output = output:gsub('%s+%f[{}%[%]%(%)%$,]','')
		output = output:gsub('([}%]%)])%f[\\%w%+%-%(%[=]', '%1 ')
		output = output:gsub(',',', ')
		output = output:gsub('%s+$', '')
		
		
		-- We now check whether the string we add will follow right
		-- after a control sequence, causing it to be interpreted
		-- as part of that control sequence.
		-- Because we want to allow the user to use stricttex, we
		-- check for alphanumerical control sequences rather than
		-- just alphabetic ones. This could add spaces that
		-- the user might not have intended, but it's a minor issue.
		if output:sub(1,1):match('%w') and content:sub(1, p-1):match('\\%w+$') then
			content = content:sub(1,p-1) .. ' ' .. output .. content:sub(p,-1)
		else
			content = content:sub(1,p-1) .. output .. content:sub(p,-1)
		end
		p, q = string.find(content, '\\SemantexIDcommand{' .. id .. '}')
	end
end

stripRemainingSemantexIDs = function()
	content = content:gsub('\\SemantexIDcommand{%d+}', '')
end

addSemtexPackageToFile = function()
	content = [[% The following was added by "stripsemantex"

\usepackage{semtex,leftindex,graphicx}

\providecommand\SemantexLeft{%
	\mathopen{}\mathclose\bgroup\left
}

\providecommand\SemantexRight{%
	\aftergroup\egroup\right
}

\providecommand\SemantexBullet{%
	\raisebox{-0.25ex}{\scalebox{1.2}{$\cdot$}}%
}
\providecommand\SemantexDoubleBullet{%
	\SemantexBullet\SemantexBullet
}

]] .. content
end