diff --git a/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.Rmd b/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.Rmd
index 489f83cef3..7dc1733e25 100644
--- a/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.Rmd
+++ b/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.Rmd
@@ -34,6 +34,10 @@ library(tidyverse)
```{r}
scratch_dir <- file.path("..", "..", "scratch")
+output_dir <- file.path(scratch_dir, "cytoband_status", "segments")
+if(!dir.exists(output_dir)) {
+ dir.create(output_dir, recursive = TRUE)
+}
```
```{r}
@@ -146,3 +150,69 @@ add_status_df %>%
output_file <- file.path("..", "..", "scratch", "consensus_seg_with_status.tsv")
write_tsv(add_status_df, output_file)
```
+
+### Prepare separate bed files for losses/gains for bedtools coverage function
+
+```{r}
+bed_status_df <- add_status_df %>%
+ select(chrom, loc.start, loc.end, everything()) %>%
+ group_by(Kids_First_Biospecimen_ID) %>%
+ arrange(chrom, loc.start, loc.end)
+
+losses_bed_status_df <- bed_status_df %>%
+ filter(status == "loss")
+
+gains_bed_status_df <- bed_status_df %>%
+ filter(status == "gain")
+
+# make lists of data frames by sample
+bed_status_list <- bed_status_df %>%
+ group_split()
+names(bed_status_list) <- bed_status_df %>%
+ group_keys() %>%
+ pull(Kids_First_Biospecimen_ID)
+
+bed_loss_list <- losses_bed_status_df %>%
+ group_split()
+names(bed_loss_list) <- losses_bed_status_df %>%
+ group_keys() %>%
+ pull(Kids_First_Biospecimen_ID)
+
+bed_gain_list <- gains_bed_status_df %>%
+ group_split()
+names(bed_gain_list) <- gains_bed_status_df %>%
+ group_keys() %>%
+ pull(Kids_First_Biospecimen_ID)
+```
+
+### Write to file
+
+```{r}
+temp <- purrr::imap(bed_status_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_callable.", .y, ".bed")
+ ),
+ col_names = FALSE))
+
+temp_loss <- purrr::imap(bed_loss_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_loss.", .y, ".bed")
+ ),
+ col_names = FALSE))
+
+temp_gain <- purrr::imap(bed_gain_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_gain.", .y, ".bed")
+ ),
+ col_names = FALSE))
+```
+
+## Session Info
+
+```{r}
+sessionInfo()
+```
+
diff --git a/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.nb.html b/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.nb.html
index 57e9efd613..723380dc69 100644
--- a/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.nb.html
+++ b/analyses/focal-cn-file-preparation/02-add-ploidy-consensus.nb.html
@@ -2955,8 +2955,8 @@ Libraries and functions
library(tidyverse)
-
-── Attaching packages ────────────────────────────────────── tidyverse 1.2.1 ──
+
+── Attaching packages ────────────────────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.2.0 ✔ purrr 0.3.2
@@ -2964,8 +2964,8 @@ Libraries and functions
✔ tidyr 0.8.3 ✔ stringr 1.4.0
✔ readr 1.3.1 ✔ forcats 0.4.0
-
-── Conflicts ───────────────────────────────────────── tidyverse_conflicts() ──
+
+── Conflicts ───────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag() masks stats::lag()
@@ -2976,8 +2976,12 @@ Libraries and functions
Files and directories
-
-scratch_dir <- file.path("..", "..", "scratch")
+
+scratch_dir <- file.path("..", "..", "scratch")
+output_dir <- file.path(scratch_dir, "cytoband_status", "segments")
+if(!dir.exists(output_dir)) {
+ dir.create(output_dir, recursive = TRUE)
+}
@@ -3113,7 +3117,7 @@ Does seg.mean agree with status?
geom_jitter()
-
+
@@ -3142,10 +3146,127 @@ Write to file
write_tsv(add_status_df, output_file)
+
+
+
+
Write to file
+
+
+
+
temp <- purrr::imap(bed_status_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_callable.", .y, ".bed")
+ ),
+ col_names = FALSE))
+
+temp_loss <- purrr::imap(bed_loss_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_loss.", .y, ".bed")
+ ),
+ col_names = FALSE))
+
+temp_gain <- purrr::imap(bed_gain_list,
+ ~ write_tsv(.x,
+ file.path(
+ output_dir, paste0("consensus_gain.", .y, ".bed")
+ ),
+ col_names = FALSE))
+
+
+
+
+
Session Info
+
+
+
+
sessionInfo()
+
+
+
R version 3.6.0 (2019-04-26)
+Platform: x86_64-pc-linux-gnu (64-bit)
+Running under: Debian GNU/Linux 9 (stretch)
+
+Matrix products: default
+BLAS/LAPACK: /usr/lib/libopenblasp-r0.2.19.so
+
+locale:
+ [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
+ [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
+ [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=C
+ [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
+ [9] LC_ADDRESS=C LC_TELEPHONE=C
+[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
+
+attached base packages:
+[1] stats graphics grDevices utils datasets methods base
+
+other attached packages:
+[1] forcats_0.4.0 stringr_1.4.0 dplyr_0.8.3 purrr_0.3.2
+[5] readr_1.3.1 tidyr_0.8.3 tibble_2.1.3 ggplot2_3.2.0
+[9] tidyverse_1.2.1
+
+loaded via a namespace (and not attached):
+ [1] Rcpp_1.0.1 cellranger_1.1.0 pillar_1.4.2 compiler_3.6.0
+ [5] base64enc_0.1-3 tools_3.6.0 digest_0.6.20 lubridate_1.7.4
+ [9] jsonlite_1.6 evaluate_0.14 nlme_3.1-140 gtable_0.3.0
+[13] lattice_0.20-38 pkgconfig_2.0.2 rlang_0.4.0 cli_1.1.0
+[17] rstudioapi_0.10 yaml_2.2.0 haven_2.1.1 xfun_0.8
+[21] withr_2.1.2 xml2_1.2.0 httr_1.4.0 knitr_1.23
+[25] generics_0.0.2 hms_0.4.2 grid_3.6.0 tidyselect_0.2.5
+[29] glue_1.3.1 R6_2.4.0 readxl_1.3.1 rmarkdown_1.13
+[33] modelr_0.1.4 magrittr_1.5 backports_1.1.4 scales_1.0.0
+[37] htmltools_0.3.6 rvest_0.3.4 assertthat_0.2.1 colorspace_1.4-1
+[41] labeling_0.3 stringi_1.4.3 lazyeval_0.2.2 munsell_0.5.0
+[45] broom_0.5.2 crayon_1.3.4
+
+
+
+
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
diff --git a/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.Rmd b/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.Rmd
new file mode 100644
index 0000000000..1f57b471ac
--- /dev/null
+++ b/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.Rmd
@@ -0,0 +1,153 @@
+---
+title: "Add dominant status column to consensus SEG file with cytoband field"
+output:
+ html_notebook:
+ toc: TRUE
+ toc_float: TRUE
+author: Chante Bethell for ALSF CCDL
+date: 2020
+---
+
+This notebook adds dominant status information per cytoband to the consensus SEG files prepared in `run-prepare-cn.sh` using the `bedtools coverage` function (these files are stored in the project's scratch directory as bed files).
+
+## Usage
+
+This notebook is intended to be run from the command line with the following (assumes you are in the root directory of the repository):
+
+```
+Rscript -e "rmarkdown::render('analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.Rmd', clean = TRUE)"
+```
+
+## Set up
+
+### Libraries and functions
+
+```{r}
+library(tidyverse)
+```
+
+### Files and directories
+
+```{r}
+scratch_dir <- file.path("..", "..", "scratch")
+```
+
+### Read in files
+
+The files we are reading in here are the bed files prepared in the shell script using `bedtools coverage`.
+
+```{r message = FALSE}
+all_callable_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_callable.bed"),
+ col_names = FALSE)
+
+loss_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_loss.bed"),
+ col_names = FALSE)
+
+gain_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_gain.bed"),
+ col_names = FALSE)
+```
+
+## Wrangle and merge consensus cytoband status data
+
+### Filter each of the cytoband status data.frames
+
+```{r}
+all_callable_cytoband_status_df <-
+ all_callable_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ band_length = X8,
+ callable_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+
+gain_cytoband_status_df <- gain_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ gain_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+
+loss_cytoband_status_df <- loss_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ loss_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+```
+
+### Join all data.frames together
+
+```{r}
+final_df <- all_callable_cytoband_status_df %>%
+ left_join(gain_cytoband_status_df,
+ by = c("chr", "cytoband", "Kids_First_Biospecimen_ID")) %>%
+ inner_join(loss_cytoband_status_df,
+ by = c("chr", "cytoband", "Kids_First_Biospecimen_ID"))
+```
+
+### Add `dominant_status` field to final data.frame
+
+```{r}
+# Create a dominant status column
+final_df <- final_df %>%
+ replace_na(list(
+ gain_fraction = 0,
+ loss_fraction = 0
+ )) %>%
+ mutate(
+ dominant_status = case_when(
+ callable_fraction < 0.5 ~ "uncallable",
+ gain_fraction / callable_fraction > 0.5 ~ "gain",
+ loss_fraction / callable_fraction > 0.5 ~ "loss",
+ (gain_fraction + loss_fraction) / callable_fraction > 0.5 ~ "unstable",
+ TRUE ~ "neutral"
+ )
+ )
+```
+
+### Add chromosome arm column
+
+```{r}
+# Add a column that tells us the position of the p or q and then use this to
+# split the cytoband column
+final_df <- final_df %>%
+ mutate(
+ cytoband_with_arm = paste0(gsub("chr", "", chr), cytoband),
+ chromosome_arm = gsub("(p|q).*", "\\1", cytoband_with_arm)
+ ) %>%
+ select(
+ Kids_First_Biospecimen_ID,
+ chr,
+ cytoband,
+ dominant_status,
+ band_length,
+ everything(),
+ -cytoband_with_arm,
+ )
+```
+
+### Display and save final table
+
+```{r}
+# Display final table with `uncallable` value added to `dominant_status` column
+final_df
+
+# Write to file
+write_tsv(final_df, file.path("results", "consensus_seg_with_ucsc_cytoband_status.tsv.gz"))
+```
+
+## Session Info
+
+```{r}
+sessionInfo()
+```
diff --git a/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.nb.html b/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.nb.html
new file mode 100644
index 0000000000..c02907ea45
--- /dev/null
+++ b/analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.nb.html
@@ -0,0 +1,3220 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Add dominant status column to consensus SEG file with cytoband field
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
This notebook adds dominant status information per cytoband to the consensus SEG files prepared in run-prepare-cn.sh using the bedtools coverage function (these files are stored in the project’s scratch directory as bed files).
+
+
Usage
+
This notebook is intended to be run from the command line with the following (assumes you are in the root directory of the repository):
+
Rscript -e "rmarkdown::render('analyses/focal-cn-file-preparation/03-add-cytoband-status-consensus.Rmd', clean = TRUE)"
+
+
+
Set up
+
+
Libraries and functions
+
+
+
+
library(tidyverse)
+
+
+
── Attaching packages ────────────────────────────────────────────── tidyverse 1.2.1 ──
+
+
+
✔ ggplot2 3.2.0 ✔ purrr 0.3.2
+✔ tibble 2.1.3 ✔ dplyr 0.8.3
+✔ tidyr 0.8.3 ✔ stringr 1.4.0
+✔ readr 1.3.1 ✔ forcats 0.4.0
+
+
+
── Conflicts ───────────────────────────────────────────────── tidyverse_conflicts() ──
+✖ dplyr::filter() masks stats::filter()
+✖ dplyr::lag() masks stats::lag()
+
+
+
+
+
+
Files and directories
+
+
+
+
scratch_dir <- file.path("..", "..", "scratch")
+
+
+
+
+
+
Read in files
+
The files we are reading in here are the bed files prepared in the shell script using bedtools coverage.
+
+
+
+
all_callable_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_callable.bed"),
+ col_names = FALSE)
+
+loss_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_loss.bed"),
+ col_names = FALSE)
+
+gain_cytoband_status_df <-
+ read_tsv(file.path(scratch_dir, "intersect_with_cytoband_gain.bed"),
+ col_names = FALSE)
+
+
+
+
+
+
+
Wrangle and merge consensus cytoband status data
+
+
Filter each of the cytoband status data.frames
+
+
+
+
all_callable_cytoband_status_df <-
+ all_callable_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ band_length = X8,
+ callable_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+
+gain_cytoband_status_df <- gain_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ gain_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+
+loss_cytoband_status_df <- loss_cytoband_status_df %>%
+ select(
+ chr = X1,
+ cytoband = X4,
+ loss_fraction = X9,
+ Kids_First_Biospecimen_ID = X10
+ ) %>%
+ filter(!is.na(cytoband))
+
+
+
+
+
+
Join all data.frames together
+
+
+
+
final_df <- all_callable_cytoband_status_df %>%
+ left_join(gain_cytoband_status_df,
+ by = c("chr", "cytoband", "Kids_First_Biospecimen_ID")) %>%
+ inner_join(loss_cytoband_status_df,
+ by = c("chr", "cytoband", "Kids_First_Biospecimen_ID"))
+
+
+
+
+
+
Add dominant_status field to final data.frame
+
+
+
+
# Create a dominant status column
+final_df <- final_df %>%
+ replace_na(list(
+ gain_fraction = 0,
+ loss_fraction = 0
+ )) %>%
+ mutate(
+ dominant_status = case_when(
+ callable_fraction < 0.5 ~ "uncallable",
+ gain_fraction / callable_fraction > 0.5 ~ "gain",
+ loss_fraction / callable_fraction > 0.5 ~ "loss",
+ (gain_fraction + loss_fraction) / callable_fraction > 0.5 ~ "unstable",
+ TRUE ~ "neutral"
+ )
+ )
+
+
+
+
+
+
Add chromosome arm column
+
+
+
+
# Add a column that tells us the position of the p or q and then use this to
+# split the cytoband column
+final_df <- final_df %>%
+ mutate(
+ cytoband_with_arm = paste0(gsub("chr", "", chr), cytoband),
+ chromosome_arm = gsub("(p|q).*", "\\1", cytoband_with_arm)
+ ) %>%
+ select(
+ Kids_First_Biospecimen_ID,
+ chr,
+ cytoband,
+ dominant_status,
+ band_length,
+ everything(),
+ -cytoband_with_arm,
+ )
+
+
+
+
+
+
Display and save final table
+
+
+
+
# Display final table with `uncallable` value added to `dominant_status` column
+final_df
+
+
+
+
+
+
# Write to file
+write_tsv(final_df, file.path("results", "consensus_seg_with_ucsc_cytoband_status.tsv.gz"))
+
+
+
+
+
+
+
Session Info
+
+
+
+
sessionInfo()
+
+
+
R version 3.6.0 (2019-04-26)
+Platform: x86_64-pc-linux-gnu (64-bit)
+Running under: Debian GNU/Linux 9 (stretch)
+
+Matrix products: default
+BLAS/LAPACK: /usr/lib/libopenblasp-r0.2.19.so
+
+locale:
+ [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
+ [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
+ [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=C
+ [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
+ [9] LC_ADDRESS=C LC_TELEPHONE=C
+[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
+
+attached base packages:
+[1] stats graphics grDevices utils datasets methods base
+
+other attached packages:
+[1] forcats_0.4.0 stringr_1.4.0 dplyr_0.8.3 purrr_0.3.2
+[5] readr_1.3.1 tidyr_0.8.3 tibble_2.1.3 ggplot2_3.2.0
+[9] tidyverse_1.2.1
+
+loaded via a namespace (and not attached):
+ [1] Rcpp_1.0.1 cellranger_1.1.0 pillar_1.4.2 compiler_3.6.0
+ [5] base64enc_0.1-3 tools_3.6.0 digest_0.6.20 lubridate_1.7.4
+ [9] jsonlite_1.6 evaluate_0.14 nlme_3.1-140 gtable_0.3.0
+[13] lattice_0.20-38 pkgconfig_2.0.2 rlang_0.4.0 cli_1.1.0
+[17] rstudioapi_0.10 yaml_2.2.0 haven_2.1.1 xfun_0.8
+[21] withr_2.1.2 xml2_1.2.0 httr_1.4.0 knitr_1.23
+[25] generics_0.0.2 hms_0.4.2 grid_3.6.0 tidyselect_0.2.5
+[29] glue_1.3.1 R6_2.4.0 readxl_1.3.1 rmarkdown_1.13
+[33] modelr_0.1.4 magrittr_1.5 backports_1.1.4 scales_1.0.0
+[37] htmltools_0.3.6 rvest_0.3.4 assertthat_0.2.1 colorspace_1.4-1
+[41] stringi_1.4.3 lazyeval_0.2.2 munsell_0.5.0 broom_0.5.2
+[45] crayon_1.3.4
+
+
+
+
+
LS0tCnRpdGxlOiAiQWRkIGRvbWluYW50IHN0YXR1cyBjb2x1bW4gdG8gY29uc2Vuc3VzIFNFRyBmaWxlIHdpdGggY3l0b2JhbmQgZmllbGQiCm91dHB1dDogCiAgaHRtbF9ub3RlYm9vazoKICAgIHRvYzogVFJVRQogICAgdG9jX2Zsb2F0OiBUUlVFCmF1dGhvcjogQ2hhbnRlIEJldGhlbGwgZm9yIEFMU0YgQ0NETApkYXRlOiAyMDIwCi0tLQoKVGhpcyBub3RlYm9vayBhZGRzIGRvbWluYW50IHN0YXR1cyBpbmZvcm1hdGlvbiBwZXIgY3l0b2JhbmQgdG8gdGhlIGNvbnNlbnN1cyBTRUcgZmlsZXMgcHJlcGFyZWQgaW4gYHJ1bi1wcmVwYXJlLWNuLnNoYCB1c2luZyB0aGUgYGJlZHRvb2xzIGNvdmVyYWdlYCBmdW5jdGlvbiAodGhlc2UgZmlsZXMgYXJlIHN0b3JlZCBpbiB0aGUgcHJvamVjdCdzIHNjcmF0Y2ggZGlyZWN0b3J5IGFzIGJlZCBmaWxlcykuCgojIyBVc2FnZQoKVGhpcyBub3RlYm9vayBpcyBpbnRlbmRlZCB0byBiZSBydW4gZnJvbSB0aGUgY29tbWFuZCBsaW5lIHdpdGggdGhlIGZvbGxvd2luZyAoYXNzdW1lcyB5b3UgYXJlIGluIHRoZSByb290IGRpcmVjdG9yeSBvZiB0aGUgcmVwb3NpdG9yeSk6CgpgYGAKUnNjcmlwdCAtZSAicm1hcmtkb3duOjpyZW5kZXIoJ2FuYWx5c2VzL2ZvY2FsLWNuLWZpbGUtcHJlcGFyYXRpb24vMDMtYWRkLWN5dG9iYW5kLXN0YXR1cy1jb25zZW5zdXMuUm1kJywgY2xlYW4gPSBUUlVFKSIKYGBgCgojIyBTZXQgdXAKCiMjIyBMaWJyYXJpZXMgYW5kIGZ1bmN0aW9ucwoKYGBge3J9CmxpYnJhcnkodGlkeXZlcnNlKQpgYGAKCiMjIyBGaWxlcyBhbmQgZGlyZWN0b3JpZXMKCmBgYHtyfQpzY3JhdGNoX2RpciA8LSBmaWxlLnBhdGgoIi4uIiwgIi4uIiwgInNjcmF0Y2giKQpgYGAKCiMjIyBSZWFkIGluIGZpbGVzIAoKVGhlIGZpbGVzIHdlIGFyZSByZWFkaW5nIGluIGhlcmUgYXJlIHRoZSBiZWQgZmlsZXMgcHJlcGFyZWQgaW4gdGhlIHNoZWxsIHNjcmlwdCB1c2luZyBgYmVkdG9vbHMgY292ZXJhZ2VgLgoKYGBge3IgbWVzc2FnZSA9IEZBTFNFfQphbGxfY2FsbGFibGVfY3l0b2JhbmRfc3RhdHVzX2RmIDwtCiAgcmVhZF90c3YoZmlsZS5wYXRoKHNjcmF0Y2hfZGlyLCAiaW50ZXJzZWN0X3dpdGhfY3l0b2JhbmRfY2FsbGFibGUuYmVkIiksCiAgICAgICAgICAgICAgICAgIGNvbF9uYW1lcyA9IEZBTFNFKQoKbG9zc19jeXRvYmFuZF9zdGF0dXNfZGYgPC0KICByZWFkX3RzdihmaWxlLnBhdGgoc2NyYXRjaF9kaXIsICJpbnRlcnNlY3Rfd2l0aF9jeXRvYmFuZF9sb3NzLmJlZCIpLAogICAgICAgICAgICAgICAgICBjb2xfbmFtZXMgPSBGQUxTRSkKCmdhaW5fY3l0b2JhbmRfc3RhdHVzX2RmIDwtCiAgcmVhZF90c3YoZmlsZS5wYXRoKHNjcmF0Y2hfZGlyLCAiaW50ZXJzZWN0X3dpdGhfY3l0b2JhbmRfZ2Fpbi5iZWQiKSwKICAgICAgICAgICAgICAgICAgY29sX25hbWVzID0gRkFMU0UpCmBgYAoKIyMgV3JhbmdsZSBhbmQgbWVyZ2UgY29uc2Vuc3VzIGN5dG9iYW5kIHN0YXR1cyBkYXRhCgojIyMgRmlsdGVyIGVhY2ggb2YgdGhlIGN5dG9iYW5kIHN0YXR1cyBkYXRhLmZyYW1lcwoKYGBge3J9CmFsbF9jYWxsYWJsZV9jeXRvYmFuZF9zdGF0dXNfZGYgPC0KICBhbGxfY2FsbGFibGVfY3l0b2JhbmRfc3RhdHVzX2RmICU+JQogIHNlbGVjdCgKICAgIGNociA9IFgxLAogICAgY3l0b2JhbmQgPSBYNCwKICAgIGJhbmRfbGVuZ3RoID0gWDgsCiAgICBjYWxsYWJsZV9mcmFjdGlvbiA9IFg5LAogICAgS2lkc19GaXJzdF9CaW9zcGVjaW1lbl9JRCA9IFgxMAogICkgJT4lCiAgZmlsdGVyKCFpcy5uYShjeXRvYmFuZCkpCgpnYWluX2N5dG9iYW5kX3N0YXR1c19kZiA8LSBnYWluX2N5dG9iYW5kX3N0YXR1c19kZiAlPiUKICBzZWxlY3QoCiAgICBjaHIgPSBYMSwKICAgIGN5dG9iYW5kID0gWDQsCiAgICBnYWluX2ZyYWN0aW9uID0gWDksCiAgICBLaWRzX0ZpcnN0X0Jpb3NwZWNpbWVuX0lEID0gWDEwCiAgKSAlPiUKICBmaWx0ZXIoIWlzLm5hKGN5dG9iYW5kKSkKCmxvc3NfY3l0b2JhbmRfc3RhdHVzX2RmIDwtIGxvc3NfY3l0b2JhbmRfc3RhdHVzX2RmICU+JQogIHNlbGVjdCgKICAgIGNociA9IFgxLAogICAgY3l0b2JhbmQgPSBYNCwKICAgIGxvc3NfZnJhY3Rpb24gPSBYOSwKICAgIEtpZHNfRmlyc3RfQmlvc3BlY2ltZW5fSUQgPSBYMTAKICApICU+JQogIGZpbHRlcighaXMubmEoY3l0b2JhbmQpKQpgYGAKCiMjIyBKb2luIGFsbCBkYXRhLmZyYW1lcyB0b2dldGhlcgoKYGBge3J9CmZpbmFsX2RmIDwtIGFsbF9jYWxsYWJsZV9jeXRvYmFuZF9zdGF0dXNfZGYgJT4lCiAgbGVmdF9qb2luKGdhaW5fY3l0b2JhbmRfc3RhdHVzX2RmLAogICAgICAgICAgICBieSA9IGMoImNociIsICJjeXRvYmFuZCIsICJLaWRzX0ZpcnN0X0Jpb3NwZWNpbWVuX0lEIikpICU+JQogIGlubmVyX2pvaW4obG9zc19jeXRvYmFuZF9zdGF0dXNfZGYsCiAgICAgICAgICAgIGJ5ID0gYygiY2hyIiwgImN5dG9iYW5kIiwgIktpZHNfRmlyc3RfQmlvc3BlY2ltZW5fSUQiKSkKYGBgCgojIyMgQWRkIGBkb21pbmFudF9zdGF0dXNgIGZpZWxkIHRvIGZpbmFsIGRhdGEuZnJhbWUKCmBgYHtyfQojIENyZWF0ZSBhIGRvbWluYW50IHN0YXR1cyBjb2x1bW4KZmluYWxfZGYgPC0gZmluYWxfZGYgJT4lCiAgcmVwbGFjZV9uYShsaXN0KAogICAgZ2Fpbl9mcmFjdGlvbiA9IDAsCiAgICBsb3NzX2ZyYWN0aW9uID0gMAogICkpICU+JQogIG11dGF0ZSgKICAgIGRvbWluYW50X3N0YXR1cyA9IGNhc2Vfd2hlbigKICAgICAgY2FsbGFibGVfZnJhY3Rpb24gPCAwLjUgfiAidW5jYWxsYWJsZSIsCiAgICAgIGdhaW5fZnJhY3Rpb24gLyBjYWxsYWJsZV9mcmFjdGlvbiA+IDAuNSB+ICJnYWluIiwKICAgICAgbG9zc19mcmFjdGlvbiAvIGNhbGxhYmxlX2ZyYWN0aW9uID4gMC41IH4gImxvc3MiLAogICAgICAoZ2Fpbl9mcmFjdGlvbiArIGxvc3NfZnJhY3Rpb24pIC8gY2FsbGFibGVfZnJhY3Rpb24gPiAwLjUgfiAidW5zdGFibGUiLAogICAgICBUUlVFIH4gIm5ldXRyYWwiCiAgICApCiAgKQpgYGAKCiMjIyBBZGQgY2hyb21vc29tZSBhcm0gY29sdW1uCgpgYGB7cn0KIyBBZGQgYSBjb2x1bW4gdGhhdCB0ZWxscyB1cyB0aGUgcG9zaXRpb24gb2YgdGhlIHAgb3IgcSBhbmQgdGhlbiB1c2UgdGhpcyB0bwojIHNwbGl0IHRoZSBjeXRvYmFuZCBjb2x1bW4KZmluYWxfZGYgPC0gZmluYWxfZGYgJT4lCiAgbXV0YXRlKAogICAgY3l0b2JhbmRfd2l0aF9hcm0gPSBwYXN0ZTAoZ3N1YigiY2hyIiwgIiIsIGNociksIGN5dG9iYW5kKSwKICAgIGNocm9tb3NvbWVfYXJtID0gZ3N1YigiKHB8cSkuKiIsICJcXDEiLCBjeXRvYmFuZF93aXRoX2FybSkKICApICU+JQogIHNlbGVjdCgKICAgIEtpZHNfRmlyc3RfQmlvc3BlY2ltZW5fSUQsCiAgICBjaHIsCiAgICBjeXRvYmFuZCwKICAgIGRvbWluYW50X3N0YXR1cywKICAgIGJhbmRfbGVuZ3RoLAogICAgZXZlcnl0aGluZygpLAogICAgLWN5dG9iYW5kX3dpdGhfYXJtLAogICkKYGBgCgojIyMgRGlzcGxheSBhbmQgc2F2ZSBmaW5hbCB0YWJsZQoKYGBge3J9CiMgRGlzcGxheSBmaW5hbCB0YWJsZSB3aXRoIGB1bmNhbGxhYmxlYCB2YWx1ZSBhZGRlZCB0byBgZG9taW5hbnRfc3RhdHVzYCBjb2x1bW4KZmluYWxfZGYKCiMgV3JpdGUgdG8gZmlsZQp3cml0ZV90c3YoZmluYWxfZGYsIGZpbGUucGF0aCgicmVzdWx0cyIsICJjb25zZW5zdXNfc2VnX3dpdGhfdWNzY19jeXRvYmFuZF9zdGF0dXMudHN2Lmd6IikpCmBgYAoKIyMgU2Vzc2lvbiBJbmZvCgpgYGB7cn0Kc2Vzc2lvbkluZm8oKQpgYGAK
+
+
+
+
+
+