Merge pull request #450 from simsong/rel-2.10

Rel 2.10

.github/workflows/continuous-integration-pip.yml

@@ -58,13 +58,20 @@ jobs:
         run: |
           echo "" | bash etc/CONFIGURE_UBUNTU22LTS.bash
 
-      - name: Make configure script
+      - name: Version Numbers
         run: |
           autoconf --version
           automake --version
           aclocal --version
           gcc --version
           g++ --version
+
+      - name: Files
+        run: |
+          find . -print
+
+      - name: Make configure script
+        run: |
           bash bootstrap.sh
 
       - name: Dump configure script
@@ -84,7 +91,7 @@ jobs:
       - name: C++ checks optimization with address-sanitizer (Mac and Linux)
         run: |
           echo === Try Address Sanitizer Optimization ===
-          ./configure --enable-address-sanitizer
+          ./configure --enable-address-sanitizer --enable-silent-rules --quiet
           make $MAKE_OPTS all
           pushd src
           make $MAKE_OPTS bulk_extractor
@@ -96,7 +103,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu-DISABLED')
         run: |
           bash bootstrap.sh
-          ./configure --enable-silent-rules --enable-thread-sanitizer
+          ./configure --enable-thread-sanitizer --enable-silent-rules  --quiet
           make clean
           make $MAKE_OPTS  all
           pushd src
@@ -109,7 +116,7 @@ jobs:
         if: startsWith(matrix.os, 'ubuntu')
         run: |
           bash bootstrap.sh
-          ./configure --disable-opt CFLAGS='-g -O0 -fprofile-arcs -ftest-coverage' CXXFLAGS='-g -O0 -fprofile-arcs -ftest-coverage' LIBS='-lgcov -lre2'
+          ./configure --disable-opt CFLAGS='-g -O0 -fprofile-arcs -ftest-coverage' CXXFLAGS='-g -O0 -fprofile-arcs -ftest-coverage' --enable-silent-rules --quiet
           make clean
           make $MAKE_OPTS  check || (echo ==error== ; cat test-suite.log; exit 1)
 
@@ -123,21 +130,11 @@ jobs:
           bash <(curl -s https://codecov.io/bash)
           popd
 
-      - uses: ammaraskar/[email protected]
-        name: GCC Problem Matcher
-
       - name: distcheck
         run: |
-          echo we are doing this because 'make distcheck' makes the source read-only and builds in a _build directory and currently that is broken
           bash bootstrap.sh
-          ./configure
-          make clean
-          make dist
-          mv bulk_extractor*.tar.gz /tmp
-          pushd /tmp
-          tar xfvz bulk_extractor*.tar.gz
-          pushd $(basename bulk_extractor*.tar.gz .tar.gz)
-          ls -l
-          ./configure
-          make check
-          popd
+          ./configure -q
+          make distcheck
+
+      - uses: ammaraskar/[email protected]
+        name: GCC Problem Matcher

.gitignore

@@ -101,3 +101,7 @@ tests/Makefile
 win32
 win64
 README
+*.auto_defs
+*.so*
+*.pdf
+*.zip

Makefile.am

@@ -7,7 +7,7 @@
 
 # We need to list *all* of the subdirs here that have Makefiles in them that are executed by
 # doing a chdir into the directory and typing 'make'. So we do not need src/be20_api
-SUBDIRS = doc doc/latex_manuals man src src/tests python specfiles tests
+SUBDIRS = doc doc/latex_manuals man src src/tests specfiles tests
 
 # Include things explicitly
 # Note - autoconf seems to automatically include the m4 rules that are used by configure.ac - no need to list them heren
@@ -18,15 +18,13 @@ SUBDIRS = doc doc/latex_manuals man src src/tests python specfiles tests
 # note - we are allowed to use wildcards below! Who knew.
 # and using $wildcard prevents it from running on mac, which doesn't use gnu make
 
-EXTRA_DIST = \
-	$(SRC_WIN_DIST) \
-	$(srcdir)/*.md \
+include Makefile.auto_defs
+
+EXTRA_DIST = $(SRC_WIN_DIST) $(AUTO_DOC_FILES) $(AUTO_ETC_FILES) $(AUTO_LICENSES) \
 	$(srcdir)/.gitignore \
-	$(srcdir)/bootstrap.sh \
-	$(srcdir)/etc/*.bash \
-	$(srcdir)/licenses/LICENSE.* \
-	$(srcdir)/*.txt \
-	$(srcdir)/src/be20_api/dfxml_cpp/src/Makefile.defs
+	$(srcdir)/CODING_STANDARDS.md \
+	$(srcdir)/LICENSE.md \
+	$(srcdir)/README.md
 
 
 # ACLOCAL_AMFLAGS = ${ACLOCAL_FLAGS} -I m4

README.md

@@ -1,46 +1,32 @@
 [![codecov](https://codecov.io/gh/simsong/bulk_extractor/branch/main/graph/badge.svg?token=3w691sdgLu)](https://codecov.io/gh/simsong/bulk_extractor)
 
-`bulk_extractor` is a high-performance digital forensics exploitation tool.
-It is a "get evidence" button that rapidly
-scans any kind of input (disk images, files, directories of files, etc)
-and extracts structured information such as email addresses, credit card numbers,
-JPEGs and JSON snippets without parsing the file
-system or file system structures. The results are stored in text files that are easily
-inspected, searched, or used as inputs for other forensic processing. bulk_extractor also creates
-histograms of certain kinds of features that it finds, such as Google search terms and email addresses,
-as previous research has shown that such histograms are especially useful in investigative and law enforcement applications.
+`bulk_extractor` is a high-performance digital forensics exploitation
+tool.  It is a "get evidence" button that rapidly scans any kind of
+input (disk images, files, directories of files, etc) and extracts
+structured information such as email addresses, credit card numbers,
+JPEGs and JSON snippets without parsing the file system or file system
+structures. The results are stored in text files that are easily
+inspected, searched, or used as inputs for other forensic
+processing. bulk_extractor also creates histograms of certain kinds of
+features that it finds, such as Google search terms and email
+addresses, as previous research has shown that such histograms are
+especially useful in investigative and law enforcement applications.
 
 Unlike other digital forensics tools, `bulk_extractor` probes every byte of data to see if it is the start of a
 sequence that can be decompressed or otherwise decoded. If so, the
 decoded data are recursively re-examined. As a result, `bulk_extractor` can find things like BASE64-encoded JPEGs and
 compressed JSON objects that traditional carving tools miss.
 
-This is the `bulk_extractor` 2.0 development branch!  For information
-about the `bulk_extractor` update, please see [Release 2.0 roadmap](https://github.com/simsong/bulk_extractor/blob/main/doc/ROADMAP_2.0.md).
+This is the `bulk_extractor` 2.1 development branch! It is reliable, but if you want to have a well-tested production quality release, download a release from https://github.com/simsong/bulk_extractor/releases.
 
 Building `bulk_extractor`
 =========================
-To build bulk_extractor in Linux or Mac OS:
+We recommend building from sources. We provide a number of `bash` scripts in the `etc/` directory that will configure a clean virtual machine.
 
-1. Start with a clean virtual machine. We recommend the current version of Fedora, as it can build both the Linux and the Windows executables. The Windows executable currently does not build under Ubuntu because of deficiencies in the mingw compiler libraries on that platform.
-
-2. Then run these commands:
-
-```
-$ git clone --recurse-submodules https://github.com/simsong/bulk_extractor.git 
-$ cd bulk_extractor/etc
-$ bash CONFIGURE_FEDORA36.bash
-$ cd ..
-$ ./bootstrap.sh
-$ ./configure
-$ make
-$ sudo make install
-```
-
-3. To compile the Windows executable, try:
+If you wish to build for Windows, you should cross-compile from a Fedora system. Start with a clean VM and use these commands:
 
 ```
-$ git clone --recurse-submodules https://github.com/simsong/bulk_extractor.git 
+$ git clone --recurse-submodules https://github.com/simsong/bulk_extractor.git
 $ cd bulk_extractor/etc
 $ bash CONFIGURE_FEDORA36_win64.bash
 $ cd ..
@@ -58,7 +44,7 @@ This release of bulk_extractor requires C++17 and has been tested to compile on
 
 * Amazon Linux as of 2023-05-25
 * Fedora 36 (most recently)
-* Ubuntu 20.04LTS 
+* Ubuntu 20.04LTS
 * MacOS 13.2.1
 
 You should *always* start with a fresh VM and prepare the system using the appropriate prep script in the `etc/` directory.

bootstrap.sh

@@ -12,6 +12,9 @@ do
   fi
 done
 
+# Makesure files are in src/Makefile.auto_defs
+python3 etc/makefile_builder.py
+
 # have automake do an initial population if necessary
 autoheader -f
 touch NEWS README AUTHORS ChangeLog

configure.ac

@@ -16,7 +16,7 @@ AC_MSG_NOTICE([at start CPPFLAGS are $CPPFLAGS])
 ## Includes
 
 AC_CONFIG_FILES([Makefile doc/Makefile doc/latex_manuals/Makefile src/Makefile src/tests/Makefile man/Makefile \
-                 python/Makefile specfiles/Makefile specfiles/bulk_extractor.spec.m4 tests/Makefile ])
+                 specfiles/Makefile specfiles/bulk_extractor.spec.m4 tests/Makefile ])
 
 AC_CONFIG_HEADERS([config.h])
 AC_CONFIG_AUX_DIR([build-aux])

doc/Makefile.am

@@ -5,21 +5,3 @@ AUTOMAKE_OPTIONS = subdir-objects
 
 DOXYGEN_FILES = doxygen/Doxyfile doxygen/Makefile doxygen/programmer_manual.doxygen doxygen/README \
 	doxygen/images/BEViewer_blank.eps doxygen/images/BEViewer_blank.png
-
-EXTRA_DIST = \
-	*.txt \
-	*.pdf \
-	*.md \
-	latex_manuals/viewerPics/*.png \
-	announce/*.txt \
-	announce/*.md \
-	bulk_extractor.html \
-	Diagnostic_Notes/be_crash_diagnostics.md \
-	Diagnostic_Notes/bulk_extractor.md
-	Diagnostic_Notes/crash_diagnosis1.txt \
-	Diagnostic_Notes/crash_diagnosis2.txt\
-	Diagnostic_Notes/debugging_performance_problems.html \
-	Diagnostic_Notes/open_source_help \
-	Diagnostic_Notes/using_gdb \
-	performance.txt \
-	$(DOXYGEN_FILES)

etc/CONFIGURE_MACOS.bash

@@ -1,5 +1,8 @@
 #!/bin/bash
-source paths.bash
+
+MYDIR=$(dirname $(readlink -f $0))
+
+source $MYDIR/paths.bash
 if [ -r /usr/local/bin/brew ]; then
     WHICH=/usr/local/bin/brew
 elif [ -r /opt/homebrew/bin/brew ]; then

etc/makefile_builder.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+
+import os
+import fnmatch
+import os.path
+
+
+config_root = {
+    'root':'.',
+    'outfile':'Makefile.auto_defs',
+    'rules':[['doc', 'AUTO_DOC_FILES', ['*.pdf',  '*.html', '*.txt', '*.md', '*.tex', '*.gitignore']],
+             ['etc', 'AUTO_ETC_FILES', ['*.bash', '*.py', '*.gitignore']],
+             ['python', 'AUTO_PYTHON_FILES', ['*.py']],
+             ['licenses', 'AUTO_LICENSES', ['*']]],
+    'ignore_fnames':[],
+    'ignore_paths':[]
+    }
+
+config_src = {
+    'root':'src',
+    'outfile':'Makefile.auto_defs',
+    'rules':[['be20_api/', 'AUTO_CPP_FILES', ['*.cpp']],
+             ['be20_api/', 'AUTO_H_FILES', ['*.h']],
+             ['tests/',    'AUTO_TESTS_DIST', ['*']],
+             ['rar/',      'AUTO_RAR_FILES', ['*.cpp','*.hpp']],
+             ['.',          'AUTO_EXTRA_DIST', ['*.md','*.am','*.txt','*.py','*.bash','.gitignore']]],
+    'ignore_fnames':set(['Makefile.am','Makefile.in',
+                         'dfxml_demo.cpp',
+                         'dfxml_version.cpp',
+                         'iblkfind.cpp',
+                         'test_dfxml.cpp',
+                         'smoke.cpp',
+                         'test_be20_api.cpp',
+                         'test_be20_threadpool.cpp'
+                         ]),
+    'ignore_paths':set(['be20_api/utfcpp/tests',
+                    'be20_api/utfcpp/samples',
+                    'be20_api/tests',
+                    'be20_api/demos'])}
+
+def build(config):
+    cwd = os.getcwd()
+    os.chdir(config['root'])
+    ignore_fnames = config['ignore_fnames']
+    ignore_paths = config['ignore_paths']
+
+    def should_ignore(full_path):
+        if os.path.basename(full_path) in ignore_fnames:
+            return True
+        for ip in ignore_paths:
+            if ip in full_path:
+                return True
+        return False
+
+    vars = dict()
+    for (start,name,pats) in config['rules']:
+        matches = []
+        for (root, dirs, files) in os.walk(start, topdown=False):
+            for fn in files:
+                for pat in pats:
+                    full_path = os.path.relpath(os.path.join(root,fn))
+                    if fnmatch.fnmatch(fn, pat) and not should_ignore(full_path):
+                        matches.append( full_path )
+        vars[name] = sorted(matches)
+    with open(config['outfile'],'w') as f:
+        for (name,matches) in vars.items():
+            if len(matches)==0:
+                continue
+            f.write(f"\n{name} = ")
+            for fname in matches:
+                f.write(f" \\\n\t{fname}")
+            f.write("\n")
+    os.chdir(cwd)
+
+if __name__=="__main__":
+    build(config_root)
+    build(config_src)

src/.gitignore

@@ -13,3 +13,4 @@ x.cpp
 domexusers.raw*
 be_graph.pdf
 *.Tpo
+Makefile.auto_defs