is a Java PDF library tool that allows creation of new PDF documents, manipulation of existing documents and the ability to extract content from documents.
| PlainText.java (pdfbox-2.0.23-src) | : | PlainText.java (pdfbox-2.0.24-src) |
|---|
| | |
| skipping to change at line 24 | | skipping to change at line 24 |
|---|
| * See the License for the specific language governing permissions and | | * See the License for the specific language governing permissions and |
| * limitations under the License. | | * limitations under the License. |
| */ | | */ |
| package org.apache.pdfbox.pdmodel.interactive.annotation.layout; | | package org.apache.pdfbox.pdmodel.interactive.annotation.layout; |
| | |
| import java.io.IOException; | | import java.io.IOException; |
| import java.text.AttributedString; | | import java.text.AttributedString; |
| import java.text.BreakIterator; | | import java.text.BreakIterator; |
| import java.text.AttributedCharacterIterator.Attribute; | | import java.text.AttributedCharacterIterator.Attribute; |
| import java.util.ArrayList; | | import java.util.ArrayList; |
|
| import java.util.Arrays; | | |
| import java.util.List; | | import java.util.List; |
| | |
| import org.apache.pdfbox.pdmodel.font.PDFont; | | import org.apache.pdfbox.pdmodel.font.PDFont; |
| | |
| /** | | /** |
| * A block of text. | | * A block of text. |
| * <p> | | * <p> |
| * A block of text can contain multiple paragraphs which will | | * A block of text can contain multiple paragraphs which will |
| * be treated individually within the block placement. | | * be treated individually within the block placement. |
| * </p> | | * </p> |
| | |
| skipping to change at line 54 | | skipping to change at line 53 |
|---|
| * Construct the text block from a single value. | | * Construct the text block from a single value. |
| * | | * |
| * Constructs the text block from a single value splitting | | * Constructs the text block from a single value splitting |
| * into individual {@link Paragraph} when a new line character is | | * into individual {@link Paragraph} when a new line character is |
| * encountered. | | * encountered. |
| * | | * |
| * @param textValue the text block string. | | * @param textValue the text block string. |
| */ | | */ |
| public PlainText(String textValue) | | public PlainText(String textValue) |
| { | | { |
|
| List<String> parts = Arrays.asList(textValue.replaceAll("\t", " ").split | | String[] parts = textValue.replace('\t', ' ').split("\\r\\n|\\n|\\r|\\u2 |
| ("\\r\\n|\\n|\\r|\\u2028|\\u2029")); | | 028|\\u2029"); |
| paragraphs = new ArrayList<Paragraph>(); | | paragraphs = new ArrayList<Paragraph>(parts.length); |
| for (String part : parts) | | for (String part : parts) |
| { | | { |
|
| // Acrobat prints a space for an empty paragraph | | // Acrobat prints a space for an empty paragraph |
| if (part.length() == 0) | | if (part.length() == 0) |
| { | | { |
| part = " "; | | part = " "; |
| } | | } |
| paragraphs.add(new Paragraph(part)); | | paragraphs.add(new Paragraph(part)); |
| } | | } |
| } | | } |
| | |
| /** | | /** |
| * Construct the text block from a list of values. | | * Construct the text block from a list of values. |
| * | | * |
| * Constructs the text block from a list of values treating each | | * Constructs the text block from a list of values treating each |
| * entry as an individual {@link Paragraph}. | | * entry as an individual {@link Paragraph}. |
| * | | * |
| * @param listValue the text block string. | | * @param listValue the text block string. |
| */ | | */ |
| public PlainText(List<String> listValue) | | public PlainText(List<String> listValue) |
| { | | { |
|
| paragraphs = new ArrayList<Paragraph>(); | | paragraphs = new ArrayList<Paragraph>(listValue.size()); |
| for (String part : listValue) | | for (String part : listValue) |
| { | | { |
| paragraphs.add(new Paragraph(part)); | | paragraphs.add(new Paragraph(part)); |
| } | | } |
| } | | } |
| | |
| /** | | /** |
| * Get the list of paragraphs. | | * Get the list of paragraphs. |
| * | | * |
| * @return the paragraphs. | | * @return the paragraphs. |
| | |
| skipping to change at line 228 | | skipping to change at line 227 |
|---|
| | |
| void setWidth(float width) | | void setWidth(float width) |
| { | | { |
| lineWidth = width; | | lineWidth = width; |
| } | | } |
| | |
| float calculateWidth(PDFont font, float fontSize) throws IOException | | float calculateWidth(PDFont font, float fontSize) throws IOException |
| { | | { |
| final float scale = fontSize/FONTSCALE; | | final float scale = fontSize/FONTSCALE; |
| float calculatedWidth = 0f; | | float calculatedWidth = 0f; |
|
| | int indexOfWord = 0; |
| for (Word word : words) | | for (Word word : words) |
| { | | { |
| calculatedWidth = calculatedWidth + | | calculatedWidth = calculatedWidth + |
| (Float) word.getAttributes().getIterator().getAttribute(
TextAttribute.WIDTH); | | (Float) word.getAttributes().getIterator().getAttribute(
TextAttribute.WIDTH); |
| String text = word.getText(); | | String text = word.getText(); |
|
| if (words.indexOf(word) == words.size() -1 && Character.isWhites
pace(text.charAt(text.length()-1))) | | if (indexOfWord == words.size() -1 && Character.isWhitespace(tex
t.charAt(text.length()-1))) |
| { | | { |
| float whitespaceWidth = font.getStringWidth(text.substring(t
ext.length()-1)) * scale; | | float whitespaceWidth = font.getStringWidth(text.substring(t
ext.length()-1)) * scale; |
| calculatedWidth = calculatedWidth - whitespaceWidth; | | calculatedWidth = calculatedWidth - whitespaceWidth; |
| } | | } |
|
| | ++indexOfWord; |
| } | | } |
| return calculatedWidth; | | return calculatedWidth; |
| } | | } |
| | |
| List<Word> getWords() | | List<Word> getWords() |
| { | | { |
| return words; | | return words; |
| } | | } |
| | |
| float getInterWordSpacing(float width) | | float getInterWordSpacing(float width) |
| | | |
| End of changes. 7 change blocks. |
|---|
| 11 lines changed or deleted | | 12 lines changed or added |
|---|
"Fossies" - the Fresh Open Source Software Archive 