1 #!/bin/bash

     2 

     3 # Relational pipes

     4 # Copyright © 2020 František Kučera (Frantovo.cz, GlobalCode.info)

     5 #

     6 # This program is free software: you can redistribute it and/or modify

     7 # it under the terms of the GNU General Public License as published by

     8 # the Free Software Foundation, version 3 of the License.

     9 #

    10 # This program is distributed in the hope that it will be useful,

    11 # but WITHOUT ANY WARRANTY; without even the implied warranty of

    12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the

    13 # GNU General Public License for more details.

    14 #

    15 # You should have received a copy of the GNU General Public License

    16 # along with this program. If not, see <http://www.gnu.org/licenses/>.

    17 

    18 

    19 # This streamlet provides a single attribute: plain text content of given PDF file. It calls the tool pdftotext.

    20 # n.b. the plain text content must fit into memory and shell variable and command-line argument (it usually will)

    21 

    22 

    23 . "$(dirname $0)/streamlet-common.sh"

    24 

    25 processMessage_WAITING_FOR_OUTPUT_ATTRIBUTES_METADATA() {

    26 	send OUTPUT_ATTRIBUTE_METADATA "${outputAttributeAliases[0]-pdftotext}"    "string"

    27 	send WAITING_FOR_INPUT_ATTRIBUTES

    28 }

    29 

    30 processMessage_WAITING_FOR_OUTPUT_ATTRIBUTES() {

    31 	value="$(pdftotext "$currentFile" - | tr -d \\f)"; # tr just removes page breaks

    32 	if   [[ "x$?" == "x0" ]]; then isNull="false"; else value=""; isNull="true"; fi

    33 	send OUTPUT_ATTRIBUTE "$value"    "$isNull";

    34 	send WAITING_FOR_INPUT_ATTRIBUTES;

    35 }

    36 

    37 initialize

    38 processMessages