From 015c00cbcc103631e1096f76cb60b6cf121fb70e Mon Sep 17 00:00:00 2001 From: Adam Sotona Date: Wed, 2 Jan 2019 14:08:43 +0100 Subject: [PATCH] fixed #49 Presplit fail --- docs/tools.md | 7 +++++-- .../java/com/msd/gin/halyard/tools/HalyardBulkLoad.java | 2 +- .../java/com/msd/gin/halyard/tools/HalyardPreSplit.java | 2 +- 3 files changed, 7 insertions(+), 4 deletions(-) diff --git a/docs/tools.md b/docs/tools.md index 364075b89..20e8b9034 100644 --- a/docs/tools.md +++ b/docs/tools.md @@ -145,7 +145,8 @@ Halyard PreSplit consumes the same RDF data sources as Halyard Bulk Load. -s,--source Source path(s) with RDF files, more paths can be delimited by comma, the paths are searched for the supported files recurrently - -t,--target Target HBase table with Halyard RDF store + -t,--target Target HBase table with Halyard RDF store, optional + HBase namespace of the target table must already exist -i,--skip-invalid Optionally skip invalid source files and parsing errors -g,--default-named-graph Optionally specify default target named graph @@ -175,7 +176,9 @@ Filesystem (HDFS) into HBase in the form of a Halyard dataset. server as a working directory for the temporary HBase files, the files are moved to their final HBase locations during the last stage of the load process - -t,--target Target HBase table with Halyard RDF store + -t,--target Target HBase table with Halyard RDF store, target table is + created if it does not exist, however optional HBase + namespace of the target table must already exist -i,--skip-invalid Optionally skip invalid source files and parsing errors -d,--verify-data-types Optionally verify RDF data type values while parsing -r,--truncate-target Optionally truncate target table just before the loading diff --git a/tools/src/main/java/com/msd/gin/halyard/tools/HalyardBulkLoad.java b/tools/src/main/java/com/msd/gin/halyard/tools/HalyardBulkLoad.java index a39995f9b..32ee3fa70 100644 --- a/tools/src/main/java/com/msd/gin/halyard/tools/HalyardBulkLoad.java +++ b/tools/src/main/java/com/msd/gin/halyard/tools/HalyardBulkLoad.java @@ -514,7 +514,7 @@ public HalyardBulkLoad() { ); addOption("s", "source", "source_paths", "Source path(s) with RDF files, more paths can be delimited by comma, the paths are searched for the supported files recurrently", true, true); addOption("w", "work-dir", "shared_folder", "Unique non-existent folder within shared filesystem to server as a working directory for the temporary HBase files, the files are moved to their final HBase locations during the last stage of the load process", true, true); - addOption("t", "target", "dataset_table", "Target HBase table with Halyard RDF store", true, true); + addOption("t", "target", "dataset_table", "Target HBase table with Halyard RDF store, target table is created if it does not exist, however optional HBase namespace of the target table must already exist", true, true); addOption("i", "skip-invalid", null, "Optionally skip invalid source files and parsing errors", false, false); addOption("d", "verify-data-types", null, "Optionally verify RDF data type values while parsing", false, false); addOption("r", "truncate-target", null, "Optionally truncate target table just before the loading the new data", false, false); diff --git a/tools/src/main/java/com/msd/gin/halyard/tools/HalyardPreSplit.java b/tools/src/main/java/com/msd/gin/halyard/tools/HalyardPreSplit.java index 3a5a167b0..4ea47b9d1 100644 --- a/tools/src/main/java/com/msd/gin/halyard/tools/HalyardPreSplit.java +++ b/tools/src/main/java/com/msd/gin/halyard/tools/HalyardPreSplit.java @@ -142,7 +142,7 @@ public HalyardPreSplit() { "Example: halyard presplit -s hdfs://my_RDF_files -t mydataset" ); addOption("s", "source", "source_paths", "Source path(s) with RDF files, more paths can be delimited by comma, the paths are searched for the supported files recurrently", true, true); - addOption("t", "target", "dataset_table", "Target HBase table with Halyard RDF store", true, true); + addOption("t", "target", "dataset_table", "Target HBase table with Halyard RDF store, optional HBase namespace of the target table must already exist", true, true); addOption("i", "skip-invalid", null, "Optionally skip invalid source files and parsing errors", false, false); addOption("g", "default-named-graph", "named_graph", "Optionally specify default target named graph", false, true); addOption("o", "named-graph-override", null, "Optionally override named graph also for quads, named graph is stripped from quads if --default-named-graph option is not specified", false, false);