From 617f56258737bd6d637b506223616c75e501a4b2 Mon Sep 17 00:00:00 2001
From: Christopher Schmied <schmied@mpi-cbg.de>
Date: Tue, 26 May 2015 20:24:10 +0200
Subject: [PATCH] BUG in Snakefile
Padding and calcluation of job_number for resave_hdf5
---
spim_registration/timelapse/Snakefile | 15 ++++++++-------
spim_registration/timelapse/export.bsh | 1 -
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/spim_registration/timelapse/Snakefile b/spim_registration/timelapse/Snakefile
index ed64a52..1fd2528 100755
--- a/spim_registration/timelapse/Snakefile
+++ b/spim_registration/timelapse/Snakefile
@@ -7,8 +7,9 @@ if JOBDIR[-1] != "/": # this checks if jobdir ends with slash if not it adds a s
#data specific config file, expected to be inside JOBDIR
configfile: "tomancak_czi.json"
-
-datasets = expand("{xml_base}-{file_id}-00.h5", xml_base=[ config["common"]["hdf5_xml_filename"].strip('\"') ],file_id=range(int(config["common"]["ntimepoints"]))) # searches JOBDIR for files that match this wildcard expression
+
+# problematic needs padding of file_id
+datasets = expand("{xml_base}-0{file_id}-00.h5", xml_base=[ config["common"]["hdf5_xml_filename"].strip('\"') ], file_id=range(int(config["common"]["ntimepoints"]))) # searches JOBDIR for files that match this wildcard expression
#TODO: this should go into a python module in this path
fre = re.compile(r'(?P<xml_base>\w+)-(?P<file_id>\d+)-00.h5')
@@ -112,7 +113,7 @@ ruleorder: define_xml_tif > define_xml_czi
rule hdf5_xml:
input: config["common"]["first_xml_filename"] + ".xml"
output: expand("{dataset}.{suffix}",dataset=[ config["common"]["hdf5_xml_filename"].strip('\"')], suffix=["xml","h5"]),
- expand("{xml_base}-{file_id}-00.h5_empty", xml_base=[ config["common"]["hdf5_xml_filename"].strip('\"') ],file_id=range(int(config["common"]["ntimepoints"])))
+ expand("{xml_base}-0{file_id}-00.h5_empty", xml_base=[ config["common"]["hdf5_xml_filename"].strip('\"') ],file_id=range(int(config["common"]["ntimepoints"]))) # problematic needs padding of file_id
log: "hdf5_xml.log"
run:
part_string = produce_string(
@@ -141,13 +142,13 @@ rule hdf5_xml:
#create dummy files according to the number of timepoints found
for index in range(int(config["common"]["ntimepoints"])):
- shell("touch {basename}-{file_id}-00.h5_empty".format(basename=config["common"]["hdf5_xml_filename"], file_id=index))
+ shell("touch {basename}-0{file_id}-00.h5_empty".format(basename=config["common"]["hdf5_xml_filename"], file_id=index)) # problematic needs padding of file_id
# resave .czi dataset as hdf5
rule resave_hdf5:
- input: "{xml_base}-{file_id}-00.h5_empty" # rules.hdf5_xml.output
- output: "{xml_base}-{file_id}-00.h5"
+ input: "{xml_base}-{file_id,\d+}-00.h5_empty" # rules.hdf5_xml.output
+ output: "{xml_base}-{file_id,\d+}-00.h5"
message: "Execute resave_hdf5 on {input}"
log: "resave_hdf5-{file_id}.log"
run:
@@ -172,7 +173,7 @@ rule resave_hdf5:
jdir=JOBDIR,
path_bsh=config["common"]["bsh_directory"] + config["resave_hdf5"]["bsh_file"],
input_xml_base="{wildcards.xml_base}",
- job_number="{wildcards.file_id}")
+ job_number=int("{wildcards.file_id}")+1) # problematic calculation not possible in cannot deal wiht wildcards file_id
part_string += "> {log} 2>&1"
shell(part_string)
diff --git a/spim_registration/timelapse/export.bsh b/spim_registration/timelapse/export.bsh
index 81b754f..ddfb174 100755
--- a/spim_registration/timelapse/export.bsh
+++ b/spim_registration/timelapse/export.bsh
@@ -46,7 +46,6 @@ hdf5_chunk_sizes = System.getProperty( "hdf5_chunk_sizes" );
timepoints_per_partition = System.getProperty( "timepoints_per_partition" );
setups_per_partition = System.getProperty( "setups_per_partition" );
int run_only_job_number = Integer.parseInt( System.getProperty( "run_only_job_number" ) );
-run_only_job_number = run_only_job_number + 1;
System.out.println( "subsampling_factors=" + subsampling_factors);
System.out.println( "hdf5_chunk_sizes=" + hdf5_chunk_sizes );
--
GitLab