replace codebase with version 2 branch

03-make-doc

@@ -0,0 +1,5 @@
+#!/bin/sh
+cd doc
+./make-doc
+
+cargo rustdoc  -p stringsext -- --document-private-items 

Cargo.toml

@@ -1,21 +1,17 @@
 [package]
 name = "stringsext"
-version = "1.7.1"
+version = "1.99.0"
 authors = ["Jens Getreu <getreu@web.de>"]
 edition = "2018"
 
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
 [dependencies]
-#encoding = { git = "https://github.com/lifthrasiir/rust-encoding" }
-# use nighly itertools with bugfix: Merge pull request #135 (2. Aug. 2016)
-# minimum version is: 0.4.17!
-#itertools = { git = "https://github.com/bluss/rust-itertools" }
-docopt = "*"
-encoding = "*"
-itertools = "*"
+encoding_rs= "*"
 lazy_static = "*"
-memmap = "*"
-rand = "*"
+docopt = "*"
 serde = "*"
 serde_derive = "*"
+itertools = "*"
 scoped_threadpool = "*"
-tempdir = "*"
+anyhow = "*"

README.md

@@ -5,10 +5,10 @@ title:    stringsext - search for multi-byte encoded strings in binary data
 
 
 **stringsext** is a Unicode enhancement of the *GNU strings* tool with
-additional functionalities: **stringsext** recognizes Cyrillic, CJKV
-characters and other scripts in all supported multi-byte-encodings,
-while *GNU strings* fails in finding any of these scripts in UTF-16 and
-many other encodings.
+additional functionalities: **stringsext** recognizes Cyrillic, Arabic, CJKV
+characters and other scripts in all supported multi-byte-encodings, while
+*GNU strings* fails in finding any of these scripts in UTF-16 and many other
+encodings.
 
 **stringsext** prints all graphic character sequences in *FILE* or
 *stdin* that are at least *MIN* bytes long.
@@ -22,14 +22,14 @@ encoding is specified, the scan is performed in different threads
 simultaneously.
 
 When searching for UTF-16 encoded strings, 96% of all possible two byte
-sequences, interpreted as UTF-16 code unit, relate directly to a Unicode
-code point. As a result, the probability of encountering valid Unicode
+sequences, interpreted as UTF-16 code unit, relate directly to Unicode
+codepoints. As a result, the probability of encountering valid Unicode
 characters in a random byte stream, interpreted as UTF-16, is also 96%.
 In order to reduce this big number of false positives, **stringsext**
-provides a parameterizable Unicode-block-filter. See **\--encodings**
+provides a parametrizable Unicode-block-filter. See **\--encodings**
 option in the manual page for more details.
 
-**stringsext** is mainly useful for determining the Unicode content of
+**stringsext** is mainly useful for extracting Unicode content out of
 non-text files.
 
 When invoked with `stringsext -e ascii -c i` **stringsext** can be used

doc/make-doc

@@ -1,23 +1,22 @@
 #!/bin/sh
-cd ..
-mkdir --parents ./doc/build/html
-mkdir --parents ./doc/build/html/_downloads
-mkdir --parents ./doc/build/man/man1
+
+mkdir --parents ./build/html
+mkdir --parents ./build/html/_downloads
+mkdir --parents ./build/man/man1
 
 # Man page
-pandoc -f markdown -t html  --include-in-header=./doc/source/docutils_basic.css\
-       ./doc/source/stringsext--man.md -o ./doc/build/html/stringsext--man.html
-pandoc -s ./doc/source/stringsext--man.md -t man \
-       -o ./doc/build/man/man1/stringsext.1
-gzip -f ./doc/build/man/man1/stringsext.1
+pandoc -f markdown -t html  --include-in-header=./source/docutils_basic.css\
+       ./source/stringsext--man.md -o ./build/html/stringsext--man.html
+pandoc -s ./source/stringsext--man.md -t man \
+       -o ./build/man/man1/stringsext.1
+gzip -f ./build/man/man1/stringsext.1
 
 # Readme page
-pandoc -f markdown -t html --include-in-header=./doc/source/docutils_basic.css\
-        ./doc/source/README.md -o ./doc/build/html/index.html
+pandoc -f markdown -t html --include-in-header=./source/docutils_basic.css\
+        ./source/README.md -o ./build/html/index.html
 
-cd  ./doc/build/html/_downloads
+cd  ./build/html/_downloads
 ln -sf ../../../../target/* .
-ln -sf ../../../../doc/build/man/man1/stringsext.1.gz .
+ln -sf ../../../build/man/man1/stringsext.1.gz .
 
 
-cargo rustdoc  -p stringsext -- --document-private-items