Ian Jauslin
summaryrefslogtreecommitdiff
path: root/bin/BBlog
blob: 141b8a51aacd2065190d8f843ec3106253c5a3f4 (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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
#!/bin/bash

## Copyright Ian Jauslin 2015-2019
## 
## Licensed under the Apache License, Version 2.0 (the "License");
## you may not use this file except in compliance with the License.
## You may obtain a copy of the License at
## 
##     http://www.apache.org/licenses/LICENSE-2.0
## 
## Unless required by applicable law or agreed to in writing, software
## distributed under the License is distributed on an "AS IS" BASIS,
## WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
## See the License for the specific language governing permissions and
## limitations under the License.

# directory containing the engine files
enginedir=/home/ian/Programs/BBlog2/src/engines

# version
version=2.1.3

function print_config {
  echo "engine: $engine"
  echo "db: $db"
  echo "conf: $conf"
  echo "aux: $aux"
  echo "format: $format"
  echo "outbib: $outbib"
  echo "order: $order" 
  echo "aux_cmd: $aux_cmd"
  echo "ref_map: $ref_map"
}

# defaults
function set_defaults {
  engine="sqlite"
  db=""
  conf=""
  aux='*.aux'
  format='\bibitem[%citeref%]{%token%}%n%%author% - {\it %title%}, %journal%, %year%.%n%'
  outbib=''
  order="alphabetical"
  aux_cmd='\\citation{'
  ref_map=''
}

# read cli args
function read_cli {

  flag=""
  for arg in "$@"; do
    case "$arg" in
      "-e" )
	flag="engine" ;;
      "-d" )
	flag="db" ;;
      "-c" )
	flag="conf" ;;
      "-a" )
	flag="aux" ;;
      "-f" )
	flag="format" ;;
      "-b" )
	flag="outbib" ;;
      "-o" )
	flag="order" ;;
      "-A" )
	flag="aux_cmd" ;;
      "-F" )
	flag="filter" ;;
      "-r" )
	flag="ref_map" ;;
      # version
      "-v" )
	echo "$version"; exit ;;
      * )
	if [ -n "$flag" ]; then
	  # treat filters differently
	  if [ "$flag" != 'filter' ]; then
	    eval "$flag='$arg'"
	    # flag the variable as set
	    eval "set_$flag=1"
	  else
	    field="${arg%%:*}"
	    value="${arg#*:}"
	    eval "filter_$field='$value'"
	    eval "set_filter_$field=1"
	  fi
	  flag=""
	fi
    esac
  done
}

# read config file
function read_config {
  extra_entries_index=0

  if [ -n "$conf" ]; then
    [ -f "$conf" ] || { echo "error: $conf: no such file" 1>&2 ; exit -1 ; }
    while read -r confline; do
      flag=""
      field="${confline%%:*}"
      value="${confline#*:}"
      # remove spaces
      field=$(echo "$field" | sed -r 's/ *$//')
      value=$(echo "$value" | sed -r 's/^ *//')
      case "$field" in
	"engine" )
	  flag="engine" ;;
	"database" )
	  flag="db" ;;
	"aux" )
	  flag="aux" ;;
	"format" )
	  flag="format" ;;
	"out_file" )
	  flag="outbib" ;;
	"order" )
	  flag="order" ;;
	"aux_cmd" )
	  flag="aux_cmd" ;;
	"ref_map" )
	  flag="ref_map" ;;
	"filter" )
	  # set flag to the specific filter
	  flag="filter_${value%%:*}"
	  # reset value
	  value="${value#*:}" ;;
	"extra" )
	  extra[$extra_entries_index]="$value"
	  extra_entries_index=$((extra_entries_index+1)) ;;
      esac

      if [ -n "$flag" ]; then
	# check it was not set on the command line
	eval "[ -n \"\$set_$flag\" -a \"\$set_$flag\" = 1 ] || $flag='$value'"
      fi
    done <"$conf"

    # sort extra entries
    if [ "$extra_entries_index" -gt 0 -a "$order" = "alphabetical" ]; then
      IFS=$'\n' extra=($(echo "${extra[*]}" | sort -k 1,1 -t :))
    fi
  fi
}

# check the configuration
function check_config {
  # check whether the engine exists
  [ -e "$enginedir/$engine.sh" ] || { echo "error: engine $engine not found in $enginedir" 1>&2; exit -1 ; }

  # check the database and aux file
  for file in "$db" "$aux"; do
    [[ "$file" =~ '*' || -e "$file" ]] || { echo "error: $file: no such file" 1>&2 ; exit -1 ; }
  done

  # check the $order variable
  [ "$order" != "alphabetical" -a "$order" != "appearance" ] && { echo "error: order should be one of 'alphabetical' or 'appearance' (read $order)" 1>&2 ; exit -1 ; }

  # check for ref_map
  [ -n "$ref_map" ] && [ ! -e "$ref_map" ] && { echo "error: $ref_map: no such file" 1>&2 ; exit -1 ; }
}

function replace_format {
  out="$1"

  # replace newlines
  out="${out//\%n\%/\\n}"

  # if the ref of the entry has been mapped, fetch the old citeref
  if [ -n "$ref_map" ]; then
    citeref=$(inverse_map_citeref "$citeref")
  fi

  # first search for conditionals
  # while '|' is still in $out
  while : ; do
    # find next '|'
    tmp=${out#*|}
    # save text before '|'
    pre=${out%%|*}
    # check whether it was found
    [ "$tmp" = "$out" ] && break
    # find next '|'
    command=${tmp%%|*}
    # save text after '|'
    post=${tmp#*|}
    # check whether it was found
    [ "$command" = "$tmp" ] && { echo "error: '|'s do not match in '$1'" 1>&2 ; exit -1 ; }

    # extract field
    field="${command%%\?*}"
    repl="${command##*\?}"

    # check whether field is empty
    val=$(eval "echo \$$field")
    if [ -n "$val" ]; then
      out="$pre$repl$post"
    else
      out="$pre$post"
    fi
  done

  # replace '%'
  # while '%' is still in $out
  while : ; do
    # find next '%'
    tmp=${out#*%}
    # check whether it was found
    [ "$tmp" = "$out" ] && break
    # find next '%'
    command=${tmp%%%*}
    # check whether it was found
    [ "$command" = "$tmp" ] && { echo "error: '%'s do not match in '$1'" 1>&2 ; exit -1 ; }

    # the field entry may be followed by a filter
    field="${command%:*}"
    # filter
    filter="${command##*:}"

    # apply filter
    if [ -n "$filter" ]; then
      sed_cmd=$(eval "echo \$filter_$filter")
      replacement=$(eval "echo \$$field" | sed -r "$sed_cmd" )
    else
      replacement=$(eval "echo \$$field")
    fi
  
    # escape '%' in replacement
    replacement="${replacement//\%/::iansays:percent::}"


    out="${out//\%$command\%/$replacement}"
  done

  # un-escape '%' in replacement
  out="${out//::iansays:percent::/\%}"

  # finish replacing newlines
  out="${out//\\n/%}"
  out=$(echo "$out" | tr "%" "\n")
  echo "$out"
}

function escape_string {
  str="$1"
  str="${str//\\/\\\\}"
  str="${str//\`/\\\`}"
  str="${str//\"/\\\"}"
  str="${str//\$/\\\$}"
  echo "$str"
}

# replace a citeref according to a ref_map
function map_citeref {
  # check whether a ref_map was specified
  [ -z "$ref_map" ] && { echo "$1" ; return 0 ; }

  oldref="$1"
  newref=$(echo "$oldref" | sed -r -f "$ref_map")
  echo "$newref"
}

# find the pre-image of a citeref through the ref_map
function inverse_map_citeref {
  # check whether a ref_map was specified
  [ -z "$ref_map" ] && { echo "$1" ; return 0 ; }

  newref="$1"

  foundref=0
  # sift through aux file
  grep -h "$aux_cmd" $aux | while read -r ref; do
    eval "ref=\${ref#$aux_cmd}"
    ref="${ref%\}}"
    # replace the ref via the ref_map
    possibleref=$(map_citeref "$ref")
    # check whether the ref is the right one
    if [ "$possibleref" = "$newref" ]; then
      echo "$ref"
      foundref=1
      return 1
    fi
  done && echo "$foundref$newref"
}

# format entries
function format_BBlog_entries {
  # keep track of tokens to avoid repetitions
  token_list=""

  has_there_been_a_nonempty_line_so_far=0

  while read -r line; do
    # if line has 0 size, then new entry
    if [ -z "$line" ]; then
      # skip if it is the first line
      if [ $has_there_been_a_nonempty_line_so_far = 1 ]; then
	# check whether an extra entry precedes it
	# alphabetical order
	if [ "$order" = "alphabetical" ]; then
	  old_token="$token"
	  old_citeref="$citeref"
	  while [[ ${#extra} -gt 0 && "${extra[0]%%:*}" < "$prauth$year" ]]; do
	    reftokval="${extra[0]#*:}"
	    citeref="${reftokval%%:*}"
	    tokval="${reftokval#*:}"
	    token="${tokval%%:*}"
	    value="${tokval#*:}"
	    # check whether token is unique
	    token=$(replace_repeated_token "$token" "$token_list")
	    # add token to list
	    token_list="$token_list;$token"

	    replace_format "$value"

	    IFS=$'\n' extra=($(echo "${extra[*]:1}"))
	  done
	  token="$old_token"
	  citeref="$old_citeref"

	  # check whether token is unique
	  token=$(replace_repeated_token "$token" "$token_list")
	  # add token to list
	  token_list="$token_list;$token"

	  replace_format "$format"
	  
	# appearance order
	else
	  foundit=0
	  if [ ${#extra} -gt 0 ]; then
	    for entry in "${extra[@]}"; do
	      ref="${entry#*:}"
	      ref="${ref%%:*}"
	      if [ "$ref" = "$citeref" ]; then
		old_token="$token"
		old_citeref="$citeref"

		citeref="$ref"
		token="${entry#*:*:}"
		value="${token#*:}"
		token="${token%%:*}"
		# check whether token is unique
		token=$(replace_repeated_token "$token" "$token_list")
		# add token to list
		token_list="$token_list;$token"

		replace_format "$value"

		token="$old_token"
		citeref="$old_citeref"
		foundit=1
		break
	      fi
	    done
	  fi

	  if [ $foundit = 0 ]; then
	    # check whether token is unique
	    token=$(replace_repeated_token "$token" "$token_list")
	    # add token to list
	    token_list="$token_list;$token"

	    replace_format "$format"
	  fi
	fi
      fi
      has_there_been_a_nonempty_line_so_far=0
    else
      eval "$line"
      has_there_been_a_nonempty_line_so_far=1
    fi
  done

  # add remaining extra entries (only for alphabetical order)
  if [ "$order" = "alphabetical" ]; then
    while [ ${#extra} -gt 0 ]; do
      reftokval="${extra[0]#*:}"
      citeref="${reftokval%%:*}"
      tokval="${reftokval#*:}"
      token="${tokval%%:*}"
      value="${tokval#*:}"
      # check whether token is unique
      token=$(replace_repeated_token "$token" "$token_list")
      # add token to list
      token_list="$token_list;$token"

      replace_format "$value"
      IFS=$'\n' extra=($(echo "${extra[*]:1}"))
    done
  fi
}

# replace a token that already exists
function replace_repeated_token {
  token="$1"
  list="$2"

  out="$token"
  i=0
  while $(echo "$token_list;" | grep -q ";$out;"); do
    i=$((i+1))
    out="$token"$(alpha_number $i)
  done

  echo "$out"
}

# convert an integer to base 26
function alpha_number {
  num="$1"
  rem="$num"
  out=""
  letters=(a b c d e f g h i j k l m n o p q r s t u v w x y z)
  while [ "$rem" -gt 0 ]; do
    digit=$((rem-26*(rem/26)))
    out="${letters[$digit]}$out"
    rem=$(((rem-digit)/26))
  done

  echo "$out"
}


set_defaults
read_cli "$@"
read_config
check_config
source "$enginedir/$engine.sh"

# check whether to order by alphabetical order or appearance
[ "$order" = "alphabetical" ] && fetch_cmd=fetch_BBlog_entries_alpha || fetch_cmd=fetch_BBlog_entries_appearance

# fetch entries
if [ -n "$outbib" ]; then
  "$fetch_cmd" | format_BBlog_entries > "$outbib"
else
  "$fetch_cmd" | format_BBlog_entries
fi