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
|
# cleanHTML.kbs - Clean the HTML downloaded from the documentation WIKI
#
# modification History
# date...... programmer... description
# 2014-08-06 j.m.reneau original coding
#
# READ THE README file in this folder to describe the use of this
# utility
#
## BE SURE THE WGET COMPLETED BEFORE RUNNING THIS PROGRAM
if version() < 1010207 then
print "requires version 1.1.2.7 or higher"
endif
debug = false
# d$ regular expressoions to remove from the downloaded HTML files
# remove an expression if it does not contain any other of the
# expressions. This way nested tags get removed in a better
# order using simple regex.
#
# These regex statements require the minimal (non-greedy)
# setting in the QRegExp libraty (see regexminimal statement)
#
dim d$[100]
nd=-1
nd++: d$[nd]= '<!--.*-->'
nd++: d$[nd]= 'doku\.php@id='
nd++: d$[nd]= '<form.*<\/form>'
nd++: d$[nd]= '<script.*<\/script>'
nd++: d$[nd]= '<div class=\"no\".*<\/div>'
nd++: d$[nd]= '<div id=\"dokuwiki__usertools\">.*<\/div>'
nd++: d$[nd]= '<div id=\"dokuwiki__sitetools\">.*<\/div>'
nd++: d$[nd]= '<div id=\"dokuwiki__pagetools\">.*<\/div>'
nd++: d$[nd]= '<div class=\"tools group\">.*<\/div>'
nd++: d$[nd]= '<div class=\"mobileTools\">.*<\/div>'
nd++: d$[nd]= '<div class=\"trace\">.*<\/div>'
nd++: d$[nd]= '<div class=\"tools\">.*<\/div>'
nd++: d$[nd]= '<div class=\"buttons\">.*<\/div>'
nd++: d$[nd]= '<div class=\"inclmeta.*<\/div>'
nd++: d$[nd]= '<ul class=\"a11y skip\">.*<\/ul>'
nd++: d$[nd]= '<span class=\"tooltip\">.*<\/span>'
nd++: d$[nd]= '<meta name=\".*>'
nd++: d$[nd]= '<link rel=\"search.*>'
nd++: d$[nd]= '<link rel=\"alternate.*>'
nd++: d$[nd]= '<link rel=\"canonical.*>'
nd++: d$[nd]= '<link rel=\"start.*>'
nd++: d$[nd]= '<link rel=\"contents.*>'
nd++: d$[nd]= '<link rel=\"shortcut.*>'
nd++: d$[nd]= '<link rel=\"apple-touch.*>'
nd++: d$[nd]= 'fetch\.php.*media='
nd++: d$[nd]= '\.php.*tseed='
nd++: d$[nd]= '<a href=\"http:\/\/www\.dokuwiki\.org.*<\/a>'
nd++: d$[nd]= '<a href=\"http:\/\/www\.php\.net.*<\/a>'
nd++: d$[nd]= '<a href=\"http:\/\/validator.*<\/a>'
nd++: d$[nd]= '<a href=\"http:\/\/jigsaw.*<\/a>'
nd++: d$[nd]= '<a href=\"http:\/\/dokuwiki\.org.*<\/a>'
file$ = dir('./wiki')
while file$ <> ""
if instrx(file$,"^doku.*html$") <> 0 then
print "processing " + file$
# read in file into string
open "./wiki/" + file$
html$ = ""
while not eof
line$ = readline
while(asc(right(line$,1))) < 32
line$ = left(line$,length(line$)-1)
if line$ = "" then exit while
end while
html$ += line$ + chr(13)
end while
close
print length(html$);
#
# find all occurrences of the expressions in the d$ array
# and delete them - if one contains another skip it until the
# inner expressions are deleted
#
regexminimal true
#
do
needchange = false
for t = 0 to nd
pos = instrx(html$,d$[t])
while pos <> 0
part$ = midx(html$, d$[t], pos)
if debug then print pos + " " + d$[t] + " " + left(part$,10) + "..." + right(part$,10) + " " + length(part$)
needchange = true
doit = true
for u = 0 to nd
if u <> t then
if instrx(part$,d$[u]) <> 0 then
doit = false
exit for
endif
endif
next u
if doit then
if debug then print "doing " + t + " " + left(part$,10) + "..." + right(part$,10) + " " + length(part$)
html$ = replace(html$,part$,"")
pos = instrx(html$, d$[t], pos)
if instr(html$,"stylesheet") = 0 then end
else
if debug then print "skipping " + left(part$,10) + "..." + right(part$,10) + " " + length(part$) + " rule " + u
pos = instrx(html$, d$[t], pos+1)
endif
end while
next t
until not needchange
#
# do some character translations and cleaning up
html$ = replace(html$,"%3A","_")
html$ = replace(html$,"%253A","_")
while instr(html$, " "+chr(13)) <> 0
html$ = replace(html$," "+chr(13),chr(13))
end while
while instr(html$, chr(13)+chr(13)) <> 0
html$ = replace(html$,chr(13)+chr(13),chr(13))
end while
#
# write file out into HTML FOLDER with good name
print " " + length(html$)
f$ = mid(file$,13,999)
f$ = replace(f$,"%3A","_")
f$ = replace(f$,"%253A","_")
print f$
open "./help/" + f$
reset
write html$
close
#
endif
file$ = dir()
end while
|
