Compare commits

...

4 Commits
v1.0.0 ... main

Author SHA1 Message Date
e0228615dc
Added bash function alternative to show simplicity 2024-12-07 14:31:27 -05:00
778fb772ec
Updated README with recon example 2024-12-07 14:21:19 -05:00
0c6927220f
Prepair for v1.0.1 2024-12-07 14:09:21 -05:00
445b6dcf26
Added make file 2024-12-07 12:11:43 -05:00
8 changed files with 194 additions and 4 deletions

34
Makefile Normal file
View File

@ -0,0 +1,34 @@
# Compiler settings
CC = gcc
CFLAGS = -Wall -Wextra -O2
PREFIX = /usr/local
VERSION = 1.0.1
# Files
PROG = shardz
SOURCES = shardz.c
OBJECTS = $(SOURCES:.c=.o)
# Targets
all: $(PROG)
$(PROG): $(OBJECTS)
$(CC) $(OBJECTS) $(CFLAGS) -o $(PROG)
install: $(PROG)
install -d $(DESTDIR)$(PREFIX)/bin
install -m 755 $(PROG) $(DESTDIR)$(PREFIX)/bin/$(PROG)
install -d $(DESTDIR)$(PREFIX)/lib/pkgconfig
install -m 644 shardz.pc $(DESTDIR)$(PREFIX)/lib/pkgconfig/
install -d $(DESTDIR)$(PREFIX)/share/man/man1
install -m 644 man/shardz.1 $(DESTDIR)$(PREFIX)/share/man/man1/
uninstall:
rm -f $(DESTDIR)$(PREFIX)/bin/$(PROG)
rm -f $(DESTDIR)$(PREFIX)/lib/pkgconfig/shardz.pc
rm -f $(DESTDIR)$(PREFIX)/share/man/man1/shardz.1
clean:
rm -f $(PROG) $(OBJECTS)
.PHONY: all install uninstall clean

View File

@ -11,11 +11,25 @@ Shardz is a lightweight C utility that shards *(splits)* the output of any proce
- Load balancing input streams
- Splitting any line-based input for distributed processing
## Building
## Building & Installation
### Quick Build
```bash
gcc -o shardz shardz.c
```
### Using Make
```bash
# Build only
make
# Build and install system-wide (requires root/sudo)
sudo make install
# To uninstall
sudo make uninstall
```
## Usage
```bash
some_command | shardz INDEX/TOTAL
@ -26,19 +40,21 @@ Where:
- `TOTAL` is the total number of shards
### Examples
Let's say you have a very large list of domains and you want to do recon on each domain. Using a single machine, this could take a very long time. However, you can split the workload across multiple machines:
- Machine number 1 would run:
```bash
curl https://example.com/large_file.txt | shardz 1/3
curl https://example.com/datasets/large_domain_list.txt | shardz 1/3 | httpx -title -ip -tech-detect -json -o shard-1.json
```
- Machine number 2 would run:
```bash
curl https://example.com/large_file.txt | shardz 2/3
curl https://example.com/datasets/large_domain_list.txt | shardz 2/3 | httpx -title -ip -tech-detect -json -o shard-2.json
```
- Machine number 3 would run:
```bash
curl https://example.com/large_file.txt | shardz 3/3
curl https://example.com/datasets/large_domain_list.txt | shardz 3/3 | httpx -title -ip -tech-detect -json -o shard-3.json
```
## How It Works
@ -50,6 +66,23 @@ Shardz uses a modulo operation to determine which lines should be processed by e
This ensures an even distribution of the workload across all shards.
## Simplicity
For what its worth, the same functionality of this tool can be done with a bash function in your `.bashrc`:
```bash
shardz() {
awk -v n="$1" -v t="$2" 'NR % t == n'
}
```
```bash
cat domains.txt | shardz 1/3 | httpx -title -ip -tech-detect -json -o shard-1.json
cat domains.txt | shardz 2/3 | httpx -title -ip -tech-detect -json -o shard-2.json
cat domains.txt | shardz 3/3 | httpx -title -ip -tech-detect -json -o shard-3.json
```
This was just a fun little project to brush up on my C, and to explore the requirements to having a package added to Linux package manager repositories.
---
###### Mirrors: [acid.vegas](https://git.acid.vegas/shardz) • [SuperNETs](https://git.supernets.org/acidvegas/shardz) • [GitHub](https://github.com/acidvegas/shardz) • [GitLab](https://gitlab.com/acidvegas/shardz) • [Codeberg](https://codeberg.org/acidvegas/shardz)

35
man/shardz.1 Normal file
View File

@ -0,0 +1,35 @@
.TH SHARDZ 1 "2025" "shardz 1.0.1" "User Commands"
.SH NAME
shardz \- shard the output of any process for distributed processing
.SH SYNOPSIS
.B some_command
.RI "|"
.B shardz
.I INDEX/TOTAL
.SH DESCRIPTION
.B shardz
is a lightweight utility that shards (splits) the output of any process for distributed processing.
It allows you to easily distribute workloads across multiple processes or machines by splitting
input streams into evenly distributed chunks.
.SH OPTIONS
.TP
.I INDEX/TOTAL
INDEX is the shard number (starting from 1), and TOTAL is the total number of shards.
.SH EXAMPLES
Machine number 1 would run:
.PP
.nf
curl https://example.com/large_file.txt | shardz 1/3
.fi
.PP
Machine number 2 would run:
.PP
.nf
curl https://example.com/large_file.txt | shardz 2/3
.fi
.SH AUTHOR
Written by acidvegas <acid.vegas@acid.vegas>
.SH COPYRIGHT
Copyright \(co 2025 acidvegas
.br
Licensed under the ISC License.

23
pkg/arch/PKGBUILD Normal file
View File

@ -0,0 +1,23 @@
# Maintainer: acidvegas <acid.vegas@acid.vegas>
pkgname=shardz
pkgver=1.0.0
pkgrel=1
pkgdesc="Utility that shards the output of any process for distributed processing"
arch=('x86_64' 'i686' 'aarch64' 'armv7h')
url="https://github.com/acidvegas/shardz"
license=('ISC')
depends=('glibc')
source=("$pkgname-$pkgver.tar.gz::$url/archive/v$pkgver.tar.gz")
sha256sums=('SKIP')
build() {
cd "$pkgname-$pkgver"
make
}
package() {
cd "$pkgname-$pkgver"
make DESTDIR="$pkgdir" PREFIX=/usr install
install -Dm644 LICENSE "$pkgdir/usr/share/licenses/$pkgname/LICENSE"
}

16
pkg/debian/control Normal file
View File

@ -0,0 +1,16 @@
Source: shardz
Section: utils
Priority: optional
Maintainer: acidvegas <acid.vegas@acid.vegas>
Build-Depends: debhelper-compat (= 13), gcc, make
Standards-Version: 4.5.1
Homepage: https://github.com/acidvegas/shardz
Package: shardz
Architecture: any
Depends: ${shlibs:Depends}, ${misc:Depends}
Description: Utility that shards process output for distributed processing
Shardz is a lightweight C utility that shards (splits) the output of any
process for distributed processing. It allows you to easily distribute
workloads across multiple processes or machines by splitting input streams
into evenly distributed chunks.

7
pkg/debian/rules Normal file
View File

@ -0,0 +1,7 @@
#!/usr/bin/make -f
%:
dh $@
override_dh_auto_install:
dh_auto_install -- PREFIX=/usr

35
pkg/rpm/shardz.spec Normal file
View File

@ -0,0 +1,35 @@
Name: shardz
Version: 1.0.1
Release: 1%{?dist}
Summary: Utility that shards the output of any process for distributed processing
License: ISC
URL: https://github.com/acidvegas/shardz
Source0: %{url}/archive/v%{version}/%{name}-%{version}.tar.gz
BuildRequires: gcc
BuildRequires: make
%description
Shardz is a lightweight C utility that shards (splits) the output of any process
for distributed processing. It allows you to easily distribute workloads across
multiple processes or machines by splitting input streams into evenly distributed chunks.
%prep
%autosetup
%build
%make_build
%install
%make_install
%files
%license LICENSE
%{_bindir}/shardz
%{_mandir}/man1/shardz.1*
%{_libdir}/pkgconfig/shardz.pc
%changelog
* Wed Dec 07 2024 acidvegas <acid.vegas@acid.vegas> - 1.0.1
- Initial package

7
shardz.pc Normal file
View File

@ -0,0 +1,7 @@
prefix=/usr/local
exec_prefix=${prefix}
bindir=${exec_prefix}/bin
Name: shardz
Description: Utility that shards the output of any process for distributed processing
Version: 1.0.1