eccc_merger.sh

   1 #!/bin/bash
   2
   3 # eccc_merger.sh - Merge Environment and Climate change Canada historical data
   4 # Copyright (C) 2020, 2021  Pierre Choffet
   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, either version 3 of the License, or
   9 # (at your option) any later version.
  10 #
  11 # This program is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 # GNU General Public License for more details.
  15 #
  16 # You should have received a copy of the GNU General Public License
  17 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  18
  19 set -e
  20
  21 # User parameters
  22 PATHS="${@}"
  23
  24 function usage() {
  25         cat <<-EOF
  26                 Merge XMLs provided by Environment and Climate change Canada
  27                 Usage: eccc_merger.sh <ECCC XML path> <ECCC XML path> [ECCC XML path […]]
  28
  29                 At least two XML files must be provided for them to be merged (obviously…).
  30                 Subsequent files will be merged as well, result is written to standard
  31                 output.
  32                 All XMLs must be valid to commons_rules.xsd and be same type (monthly or
  33                 almanach)
  34                 EOF
  35         exit
  36 }
  37
  38 # Auto detect input types
  39 MERGE_TYPE=''
  40 for path in $@
  41 do
  42         # Check file exists
  43         if [ ! -f "${path}" ]
  44         then
  45                 echo "File ${path} doesn't exist" >&2
  46                 exit 1
  47         fi
  48
  49         # Check merge type
  50         FILE_TYPE=$(xmlstarlet sel -t -i '/climatedata/month' -o almanach --elif '/climatedata/stationdata' -o monthly --else -o ''  "${path}")
  51
  52         if [ "${MERGE_TYPE}" != '' ]
  53         then
  54                 if [ "${FILE_TYPE}" != "${MERGE_TYPE}" ]
  55                 then
  56                         echo 'All XMLs must be the same type' >&2
  57                         exit 1
  58                 fi
  59         else
  60                 MERGE_TYPE="${FILE_TYPE}"
  61         fi
  62 done
  63
  64 # Select stylesheet to be used
  65 if [ "${MERGE_TYPE}" == 'almanach' ]
  66 then
  67         STYLESHEET='eccc_merger_almanach.xslt'
  68 elif [ "${MERGE_TYPE}" == 'monthly' ]
  69 then
  70         STYLESHEET='eccc_merger_monthly.xslt'
  71         echo 'Not working with monthly data for now. Exiting.'
  72         exit
  73 fi
  74
  75 # Merge
  76 FIRST_PASS=1
  77 for path in ${PATHS}
  78 do
  79         if [ "${FIRST_PASS}" -eq 1 ]
  80         then
  81                 FIRST_PASS=0
  82                 FIRST_PATH="$(mktemp)"
  83                 cp "${path}" "${FIRST_PATH}"
  84                 continue
  85         fi
  86
  87         SECOND_PATH="${path}"
  88         OUT_PATH="$(mktemp)"
  89         xmlstarlet tr "${STYLESHEET}" -s "merge-path=${SECOND_PATH}" "${FIRST_PATH}" > "${OUT_PATH}"
  90
  91         rm "${FIRST_PATH}"
  92         FIRST_PATH="${OUT_PATH}"
  93 done
  94
  95 cat "${OUT_PATH}"
  96 rm "${OUT_PATH}"