Merge branch 'main' of github.com:pkiraly/qa-catalogue

pkiraly · Feb 3, 2025 · 48a3791 · 48a3791
2 parents 2e7bfa4 + 6641414
commit 48a3791
Show file tree

Hide file tree

Showing 39 changed files with 389 additions and 223 deletions.
diff --git a/.travis.yml b/.travis.yml
diff --git a/README.md b/README.md
@@ -1100,7 +1100,10 @@ or with a bash script
 
 options:
 * [general parameters](#general-parameters)
-* `-f`, `--format`: the name of the format (at time of writing there is no any)
+* `-f`, `--format`: the MARC output format
+  * if not set, the output format follows the examples in the MARC21 
+    documentation (see the example below)
+  * `xml`: the output will be MARCXML
 * `-c <number>`, `-countNr <number>`: count number of the record (e.g. 1 means
   the first record)
 * `-s [path=query]`, `-search [path=query]`: print records matching the query.
@@ -1118,6 +1121,8 @@ options:
   (default: TAB)
 * `-e <file>`, `--fileName <file>`: the name of report the program produces
   (default: `extracted.csv`)
+* `-A <identifiers>`, `--ids <identifiers>`: a comma separated list of record 
+  identifiers 
 
 The output of displaying a single MARC record is something like this one:
 
@@ -1823,6 +1828,7 @@ options:
   with `_txt`). \[This parameter is available from v0.8.0\]
 * `-D <int>`, `--commitAt <int>`: commit index after this number of records \[This parameter is available from v0.8.0\]
 * `-E`, `--indexFieldCounts`: index the count of field instances \[This parameter is available from v0.8.0\]
+* `-G`, `--indexSubfieldCounts`: index the count of subfield instances \[This parameter is available from v0.8.0\]
 * `-F`, `--fieldPrefix <arg>`: field prefix
 
 The `./index` file (which is used by `catalogues/[catalogue].sh` and `./qa-catalogue` scripts) has additional parameters:

diff --git a/avram-schemas/validate-schemas b/avram-schemas/validate-schemas
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 validate() {
-  npm run --silent avram -- -s $@
+  npm run --silent avram -- -s "$1"
 }
 
 validate avram-schemas/marc-schema.json

diff --git a/catalogues/k10plus_pica_grouped.sh b/catalogues/k10plus_pica_grouped.sh
@@ -16,7 +16,8 @@ TYPE_PARAMS="$TYPE_PARAMS --allowableRecords base64:"$(echo '[email protected] !~ "^L" && 0
 # TYPE_PARAMS="$TYPE_PARAMS --solrUrl http://localhost:8983/solr/k10plus_pica_grouped"
 TYPE_PARAMS="$TYPE_PARAMS --solrForScoresUrl http://localhost:8983/solr/k10plus_pica_grouped_validation"
 TYPE_PARAMS="$TYPE_PARAMS --indexWithTokenizedField"
-TYPE_PARAMS="$TYPE_PARAMS --indexFieldCounts"
+TYPE_PARAMS="$TYPE_PARAMS --indexFieldCounts --indexSubfieldCounts"
+TYPE_PARAMS="$TYPE_PARAMS --fieldPrefix bib"
 # MASK=sample.pica
 # =kxp-title_2022-09-30-groupped.dat.gz
 MASK=${MASK:=pica-with-holdings-info-1K.dat} # if not set in setdir.sh

diff --git a/catalogues/mokka.sh b/catalogues/mokka.sh
@@ -5,7 +5,7 @@
 . ./setdir.sh
 
 NAME=mokka
-TYPE_PARAMS="--marcxml --emptyLargeCollectors"
+TYPE_PARAMS="--marcxml --emptyLargeCollectors --indexWithTokenizedField"
 # TYPE_PARAMS="--marcVersion SZTE"
 MASK=all.xml.gz
 

diff --git a/catalogues/nls.sh b/catalogues/nls.sh
@@ -5,7 +5,10 @@
 . ./setdir.sh
 
 NAME=nls
-TYPE_PARAMS="--marcxml --emptyLargeCollectors --indexWithTokenizedField --indexFieldCounts --solrForScoresUrl http://localhost:8983/solr/nls_validation"
+TYPE_PARAMS="--marcxml --emptyLargeCollectors --indexWithTokenizedField --doCommit"
+# TYPE_PARAMS="${TYPE_PARAMS} --offset 180000"
+TYPE_PARAMS="${TYPE_PARAMS} --indexFieldCounts --indexSubfieldCounts"
+TYPE_PARAMS="${TYPE_PARAMS} --solrForScoresUrl http://localhost:8983/solr/nls_validation"
 MASK=NBS_v2_validated_marcxml.xml.gz
 
 . ./common-script
diff --git a/cli-parameter-definitions.json b/cli-parameter-definitions.json
@@ -294,6 +294,12 @@
       "hasArg": false,
       "description": "index the count of field instances"
     },
+    {
+      "short": "G",
+      "long": "indexSubfieldCounts",
+      "hasArg": false,
+      "description": "index the count of subfield instances"
+    },
     {
       "short": "F",
       "long": "fieldPrefix",
@@ -426,6 +432,12 @@
       "long": "fileName",
       "hasArg": true,
       "description": "output file (default: extracted.csv)"
+    },
+    {
+      "short": "A",
+      "long": "ids",
+      "hasArg": true,
+      "description": "list of identifiers separated by comma"
     }
   ],
   "functional-analysis": [
@@ -462,6 +474,7 @@
       "description": "action: 'primary' (default), 'pairing'"
     }
   ],
+  "marc-history": [],
   "record-patterns": [
     {
       "short": "R",